---
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
datasets:
- SupraLabs/reasoning-corpus-4K-5M-v1
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
language:
- en
tags:
- smollm2
- reasoning
- supervised-fine-tuning
- chat
- transformers
- safetensors
---

# SmolLM2-135M Reasoning-5K

A full-parameter reasoning fine-tune of
[`HuggingFaceTB/SmolLM2-135M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) using 5,000 examples
sampled from [`SupraLabs/reasoning-corpus-4K-5M-v1`](https://huggingface.co/datasets/SupraLabs/reasoning-corpus-4K-5M-v1).

The model was trained to place its reasoning trace inside `<think>` and
`</think>` tags, followed by a separate final answer.

## Training summary

| Setting | Value |
|---|---:|
| Training examples | 5,000 |
| Evaluation examples | 128 |
| Epochs | 2 |
| Maximum sequence length | 4,096 tokens |
| Learning rate | 3e-05 |
| Training objective | Assistant-only causal cross-entropy |
| Parameter training | Full model |
| Precision | bfloat16/float16 depending on training GPU |

The system and user portions were masked from the loss. Samples exceeding the
maximum context length were rejected instead of being cut through the middle of
a reasoning trace.

## Usage

```python
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))
```

## Reasoning format

The expected assistant format is:

```text
<think>
Internal reasoning trace
</think>

Final answer
```

This small model is experimental. It should not be assumed to produce correct
reasoning merely because it emits a structured reasoning trace.

## Files

`training_info.json` records the training configuration, any metrics found in
the local output directory, and SHA-256 hashes of the uploaded weight files.

## License

The model follows the Apache 2.0 license used by the base SmolLM2 model. Review
the base model repository and source dataset for their complete terms.