Ma7ee7/SmolLM2-135M-Reasoning-5K

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "YOUR_USERNAME/SmolLM2-135M-Reasoning-5K"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {
        "role": "system",
        "content": 'You are a helpful AI assistant. For difficult problems, reason carefully inside <think> and </think> tags, then provide a clear final answer.',
    },
    {
        "role": "user",
        "content": "A farmer has 17 sheep. All but 9 run away. How many remain?",
    },
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
).to(model.device)

with torch.inference_mode():
    output = model.generate(
        **inputs,
        max_new_tokens=256,
        do_sample=False,
        repetition_penalty=1.05,
    )

new_tokens = output[0, inputs["input_ids"].shape[1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=False))

<think>
Internal reasoning trace
</think>

Final answer