Tess-v2.5.2-Qwen2-72B

10

11

—

by

migtissera

Language Model

OTHER

72B params

New

10 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

161GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

68GB+ RAM

Code Examples

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Sample code to run inferencepythontransformers

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer
from stop_word import StopWordCriteria

model_path = "migtissera/Tess-v2.5.2-Qwen2-72B"
output_file_path = "/home/migel/conversations.jsonl"

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit=False,
    trust_remote_code=True,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

terminators = [
    tokenizer.convert_tokens_to_ids("<|im_end|>")
]

def generate_text(instruction):
    tokens = tokenizer.encode(instruction)
    tokens = torch.LongTensor(tokens).unsqueeze(0)
    tokens = tokens.to("cuda")

    instance = {
        "input_ids": tokens,
        "top_p": 1.0,
        "temperature": 0.75,
        "generate_len": 1024,
        "top_k": 50,
    }

    length = len(tokens[0])
    with torch.no_grad():
        rest = model.generate(
            input_ids=tokens,
            max_length=length + instance["generate_len"],
            use_cache=True,
            do_sample=True,
            top_p=instance["top_p"],
            temperature=instance["temperature"],
            top_k=instance["top_k"],
            num_return_sequences=1,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=terminators,
        )
    output = rest[0][length:]
    string = tokenizer.decode(output, skip_special_tokens=True)
    return f"{string}"

conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation.<|im_end|>\n<|im_start|>user\n"""

while True:
    user_input = input("You: ")
    llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
    answer = generate_text(llm_prompt)
    print(answer)
    conversation = f"{llm_prompt}{answer}\n"
    json_data = {"prompt": user_input, "answer": answer}

    with open(output_file_path, "a") as output_file:
        output_file.write(json.dumps(json_data) + "\n")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.