README.md

---
library_name: peft
base_model: deepseek-ai/deepseek-coder-1.3b-base
pipeline_tag: text-generation
tags:
- code
- program-repair
- vulnerability-repair
- peft
- lora
- synthfix
- router
- pyrepair
---

# SynthFix deepseek-coder-1.3b-base (pyrepair)

This repository contains the SynthFix LoRA repair-agent adapter and matching router checkpoint for **Python functional repair** on **pyrepair**.

SynthFix is an adaptive neuro-symbolic code repair framework. During training, a lightweight router chooses between supervised fine-tuning (SFT) and reward fine-tuning (RFT), while the reward combines compiler-, analyzer-, and test-derived symbolic evidence. At inference time, the same evidence supports best-of-K candidate selection with a greedy floor.

## Contents

- `adapter_model.safetensors`, `adapter_config.json`: PEFT/LoRA adapter for `deepseek-ai/deepseek-coder-1.3b-base`.
- tokenizer files copied from the training checkpoint.
- `router.pt`: PyTorch state dict for the SynthFix router associated with this adapter.

## Base Model

This adapter is intended to be loaded with `deepseek-ai/deepseek-coder-1.3b-base` using `peft.PeftModel.from_pretrained`.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "deepseek-ai/deepseek-coder-1.3b-base"
adapter_id = "CoderDoge/synthfix-deepseek-coder-1.3b-pyrepair"

tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(base_model, trust_remote_code=True)
model = PeftModel.from_pretrained(base, adapter_id)
```

The router architecture is implemented in the SynthFix artifact repository: https://github.com/CoderDoge1108/SynthFix and https://github.com/largehappygroup/SynthFix.

## Paper

SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair

- arXiv: https://arxiv.org/abs/2604.17184
- GitHub artifact: https://github.com/CoderDoge1108/SynthFix

## Notes

These are adapter weights rather than full copies of the base models. Users should follow the license and usage terms of the corresponding base model.