README.md

metadata

title: Code2LoRA Timeline
emoji: 🧬
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.50.0
app_file: app.py
pinned: true
license: mit
short_description: Generate a repo-specific LoRA at any commit and test it.
models:
  - code2lora/code2lora-gru
  - Qwen/Qwen2.5-Coder-1.5B
datasets:
  - code2lora/code2lora-evo

Code2LoRA: watch an adapter learn a repository, commit by commit

Pick one of the held-out test repositories from RepoPeftBench, move through its commit history, generate the Code2LoRA-Evo adapter at any commit, and compare the adapted Qwen2.5-Coder-1.5B with the plain base model on the test assertions that commit introduced, or on your own code prefix.

• Adapt runs the hypernetwork head live on the precomputed GRU state of the selected commit and injects the resulting rank-16 LoRA into the frozen base model.
• Cached predictions were produced on a GPU with exactly the same adapter, prompt (≤ 4,096 tokens) and scoring as the paper; Run live regenerates them here.
• tools/ contains the scripts that built data/ from the published dataset and checkpoint.

Paper: arXiv 2606.06492 · Product: code2lora.app · CLI: pip install code2lora