---
license: apache-2.0
language:
- en
tags:
- text-generation
- grammar-correction
- grammatical-error-correction
- gec
- style-preserving
- dpo
- sft
- smollm
- small-language-model
- writing-assistant
- proofreading
- nlp
base_model: HuggingFaceTB/SmolLM-135M
datasets:
- jfleg
pipeline_tag: text-generation
model-index:
- name: SmolLM-135M-GEC-SFT-DPO
  results:
  - task:
      type: text-generation
      name: Grammar Correction
    metrics:
    - type: bleu
      value: 0.50
      name: BLEU
---

# SmolLM-135M-GEC-SFT-DPO

A **style-preserving grammar correction** model based on SmolLM-135M, trained with SFT + DPO to make minimal, targeted corrections while preserving your original writing style.

## Why This Model?

Unlike large language models (GPT, Claude, etc.) that tend to rewrite entire sentences, this model makes **minimal, targeted corrections** - fixing only grammatical errors while preserving your vocabulary, tone, and voice. Perfect for:

- **Legal documents**: Maintain precise legal terminology
- **Academic writing**: Preserve scholarly tone
- **ESL/EFL education**: Help learners without changing their ideas
- **Professional communications**: Keep your authentic voice

## Key Features

- **Minimal corrections**: Fixes only grammatical errors, doesn't rewrite your sentences
- **Style preservation**: Maintains your vocabulary, tone, and voice
- **Small & efficient**: Only 135M parameters (~500MB) - runs on CPU!
- **BLEU score**: ~0.50 on grammar correction benchmarks

## Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("DanJZY/SmolLM-135M-GEC-SFT-DPO")
tokenizer = AutoTokenizer.from_pretrained("DanJZY/SmolLM-135M-GEC-SFT-DPO")

text = "As the number of people grows, the need of habitable environment is essential."
inputs = tokenizer(f"Fix grammar: {text}", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Example: Style-Preserving vs Over-Correction

```
Original (with error):
"As the number of people grows, the need of habitable environment is essential."

✅ Our Model (Style-Preserving):
"As the number of people grows, the need for a habitable environment is essential."
                                         ↑
                            Only fixes "of" → "for a"

❌ Typical Model (Over-Correction):
"As population growth continues, the necessity for a habitable environment becomes essential."
                            ↑
    Completely rewrites: changes vocabulary, structure, and tone
```

## Training Details

| Parameter | Value |
|-----------|-------|
| Base model | [SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) |
| Training method | SFT + DPO (Direct Preference Optimization) |
| Preference pairs | ~19,000 (generated using edit distance) |
| Total experiments | 28 (22 SFT + 6 DPO/IPO) |
| Hardware | 8x RTX 3090 |
| Training time | ~3 hours |

## Resources

| Resource | Link |
|----------|------|
| GitHub Repository | [ZhuoyuanJiang/SmolLM-GEC-SFT-DPO](https://github.com/ZhuoyuanJiang/SmolLM-GEC-SFT-DPO) |
| Full Experiment Checkpoints | [Google Drive](https://drive.google.com/drive/folders/1fxd_yi4r4crp7UK3tJVKxVPHo9gRcw4z) (~68GB) |
| Training Notebooks | [GitHub notebooks/](https://github.com/ZhuoyuanJiang/SmolLM-GEC-SFT-DPO/tree/main/notebook) |

## Intended Use

- Grammar correction for English text
- Writing assistance that preserves author's voice
- Educational tools for language learners
- Proofreading applications

## Limitations

- English only
- Best for sentence-level corrections
- Not designed for stylistic improvements (only grammar)

## Citation

```bibtex
@misc{smollm_gec_sft_dpo_2025,
  title={SmolLM-135M-GEC-SFT-DPO: Style-Preserving Grammar Correction with Direct Preference Optimization},
  author={Zhuoyuan Jiang},
  year={2025},
  url={https://huggingface.co/DanJZY/SmolLM-135M-GEC-SFT-DPO},
  note={Fine-tuned SmolLM-135M for minimal, style-preserving grammatical error correction}
}
```

## Acknowledgments

Special thanks to **Nima Tajbakhsh** (Nvidia) for guidance on efficient training methods.