Mistral-Nemo-Instruct-2407-abliterated

180

19

9 languages

license:apache-2.0

by

natong19

Other

OTHER

New

180 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Code Examples

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

Key featurespythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "natong19/Mistral-Nemo-Instruct-2407-abliterated"
device = "cuda"

tokenizer = AutoTokenizer.from_pretrained(model_id)

conversation = [{"role": "user", "content": "Where's the capital of France?"}]

tool_use_prompt = tokenizer.apply_chat_template(
            conversation,
            tokenize=False,
            add_generation_prompt=True,
)

inputs = tokenizer(tool_use_prompt, return_tensors="pt", return_token_type_ids=False).to(device)

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")

outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][len(inputs["input_ids"][0]):], skip_special_tokens=True))

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.