ThinkAgain1.6-S2

Name: ThinkAgain1.6-S2
Author: beyoru

2 languages

—

beyoru

Language Model

OTHER

New

1 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

Model detail No system prompt training\ LoRA training rank 64 and alpha 128\ Tool calling support

Code Examples

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

Model detailtexttransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

MAX_REASONING_TOKENS = 4096
MAX_RESPONSE_TOKENS = 1024

model_name = "beyoru/ThinkAgain1.6-S2"

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = []

def stream_output(output_text):
    for char in output_text:
        print(char, end="", flush=True)

while True:
    prompt = input("USER: ")
    
    messages.append({"role": "user", "content": prompt})
    
    # Generate reasoning
    reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
    reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
    reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
    reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "reasoning", "content": reasoning_output})
    
    print("REASONING: ", end="")
    stream_output(reasoning_output)
    print()
    
    # Generate answer
    response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
    response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
    response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)
    
    messages.append({"role": "assistant", "content": response_output})
    
    print("ASSISTANT: ", end="")
    stream_output(response_output)
    print()

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.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.