Elib27
/

qwen2.5-0.5b-commit-msg-lora

commit-message-generation

conventional-commits

Model card Files Files and versions

Qwen2.5-0.5B-Instruct — Commit Message LoRA Adapter

LoRA adapter fine-tuned on top of Qwen/Qwen2.5-0.5B-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.

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Elib27/qwen2.5-0.5b-commit-msg-lora

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Adapter

(645)

this model

Collection including Elib27/qwen2.5-0.5b-commit-msg-lora

Teaching Small LLMs to Write Git Commits

Dataset + LoRA adapters for fine-tuning small LLMs to write Conventional Commits from a git diff. Part of a local, offline commit-message tool. • 7 items • Updated about 5 hours ago