LIMO-v2

124

2

license:apache-2.0

by

GAIR

Other

OTHER

2502.03387B params

New

124 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

5593GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

2331GB+ RAM

Code Examples

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

Using HF Transformerspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "GAIR/LIMO-v2",
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("GAIR/LIMO-v2", trust_remote_code=True)

# Prepare input messages
messages = [
    {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
    {"role": "user", "content": "What is the result of 1+1?"}
]

# Format input using chat template
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

# Tokenize input
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
outputs = model.generate(
    **inputs,
    max_new_tokens=32768,
    temperature=0.7,
    top_p=0.95,
    do_sample=True
)

# Decode and print response
response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(response)

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.