Hugging Face's logo

Elib27
/
llama-3.2-1b-commit-msg-lora

PEFT
Safetensors
lora
commit-message-generation
conventional-commits
code
Model card Files
xet
 Community
llama-3.2-1b-commit-msg-lora / README.md
Elib27's picture
Elib27
Upload README.md with huggingface_hub
9a909c5 verified
preview code
|
Raw
History Blame Contribute Delete
989 Bytes
metadata 
base_model: meta-llama/Llama-3.2-1B-Instruct
library_name: peft
tags:
  - lora
  - commit-message-generation
  - conventional-commits
  - code

Llama-3.2-1B-Instruct — Commit Message LoRA Adapter

LoRA adapter fine-tuned on top of meta-llama/Llama-3.2-1B-Instruct to generate Conventional Commits messages from a git diff.

Part of a project to build a local, offline prepare-commit-msg git hook. Full write-up: https://eliotbas.com/projects/commits-fine-tuning/ Training dataset: https://huggingface.co/datasets/Elib27/commits

Training details

  • Method: LoRA (r=16, alpha=32)
  • Framework: Unsloth + TRL SFTTrainer
  • Hardware: Google Colab A100
  • Dataset: ~11k (diff, commit message) pairs, see eliotbas/commits

See the article for full evaluation results (ROUGE-L, structural checks, LLM-as-judge) across all model sizes.