Hi, I’m Seniru Epasinghe 👋

I’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.

---

🌐 Connect with me

---

• Developed by: seniruk
• License: apache-2.0
• Finetuned from model : unsloth/Qwen2.5-Coder-1.5B-Instruct

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

---

base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct tags:

• text-generation-inference
• transformers
• unsloth
• qwen2
• trl license: apache-2.0 language:
• en

---

---

datasets:

• bigcode/commitpackft

---

Purpose

Used for generating high quality commit messages for a given git difference

Model Description

Generated by fine tuning Qwen2.5-Coder-1.5B-Instruct on bigcode/commitpackft dataset for 2 epochs Trained on a total of 277 Languages Achieved a final training loss in the range of 1- 1.7 (due to data set not containing equal data rows for each language) For common languages(python, java ,javascripts,c etc) loss went for a minimum of 1.0335

Environmental Impact

• Hardware Type: geforce RTX 4060 TI - 16GB]
• Hours used: 10 Hours
• Cloud Provider: local

Results

Inference input format (If using API mostly)

<|im_start|>system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>
<|im_start|>user
{instructions}
{git_diff}<|im_end|>
<|im_start|>assistant

And the model will predict the rest of the content -> {assistant output}<|im_end|>