--- license: apache-2.0 language: - en base_model: - Qwen/Qwen2.5-Coder-0.5B pipeline_tag: text-generation datasets: - seniruk/git-diff_to_commit_msg_large --- # Hi, Iā€™m Seniru Epasinghe šŸ‘‹ Iā€™m an AI undergraduate and an AI enthusiast, working on machine learning projects and open-source contributions. I enjoy exploring AI pipelines, natural language processing, and building tools that make development easier. --- ## šŸŒ Connect with me [![Hugging Face](https://img.shields.io/badge/Hugging%20Face-seniruk-orange?logo=huggingface&logoColor=white)](https://huggingface.co/seniruk)    [![Medium](https://img.shields.io/badge/Medium-seniruk_epasinghe-black?logo=medium&logoColor=white)](https://medium.com/@senirukepasinghe)    [![LinkedIn](https://img.shields.io/badge/LinkedIn-seniru_epasinghe-blue?logo=linkedin&logoColor=white)](https://www.linkedin.com/in/seniru-epasinghe-b34b86232/)    [![GitHub](https://img.shields.io/badge/GitHub-seth2k2-181717?logo=github&logoColor=white)](https://github.com/seth2k2) ### Finetuned-qwen2.5-coder-0.5B model on 100000 rows of a cutom dataset containing. git-differences and respective commit messages - [dataset huggingface link](https://huggingface.co/datasets/seniruk/git-diff_to_commit_msg_large) - [dataset kaggle link](https://www.kaggle.com/datasets/seniruepasinghe/git-diff-to-commit-msg-large) ### Each row of the dataset was formatted as below to suit finetuning requirement of Qwen2.5-coder model so we have to use the same prompt for better results ``` """Generate a concise and meaningful commit message based on the provided Git diff. ### Git Diff: {Git diff from dataset} ### Commit Message:""" ``` ### Code for inference of the gguf model is given below ``` from llama_cpp import Llama modelGGUF = Llama.from_pretrained( repo_id="seniruk/qwen2.5coder-0.5B_commit_msg", filename="qwen0.5-finetuned.gguf", rope_scaling={"type": "linear", "factor": 2.0}, chat_format=None, # Disables any chat formatting n_ctx=32768, # Set the context size explicitly ) # Define the commit message prompt (Minimal format, avoids assistant behavior) commit_prompt = """Generate a meaningful commit message explaining all the changes in the provided Git diff. ### Git Diff: {} ### Commit Message:""" # Removed {} after "Commit Message:" to prevent pre-filled text. # Git diff example for commit message generation git_diff_example = """ diff --git a/index.html b/index.html index 89abcde..f123456 100644 --- a/index.html +++ b/index.html @@ -5,16 +5,6 @@

Welcome to My Page

- - - - - - - - - -
NameAge
John Doe30
+

This is a newly added paragraph replacing the table.

""" # Prepare the raw input prompt input_prompt = commit_prompt.format(git_diff_example) # Generate commit message output = modelGGUF( input_prompt, max_tokens=64, temperature=0.6, # Balanced randomness top_p=0.8, # Controls nucleus sampling top_k=50, # Limits vocabulary selection ) # Decode and print the output commit_message = output["choices"][0]["text"].strip() print("\nGenerated Commit Message:\n{}".format(commit_message)) ```