zetavg/LLaMA-LoRA-Tuner
A web UI and Colab notebook for fine-tuning LLaMA, GPT-J and similar models using LoRA, with a Gradio-based chat interface for demonstration.
Not currently ranked — collecting fresh signals.
star history
LLaMA-LoRA Tuner provides a graphical interface for parameter-efficient fine-tuning of large language models via Low-Rank Adaptation. It supports multiple base models including LLaMA, GPT-J, GPT4All-J, Dolly, and Pythia, and offers one-click Colab deployment. The project includes a Gradio-based chat UI to demonstrate fine-tuned models interactively, and handles dataset loading in JSON/JSONL formats.
Frequently asked
- What is zetavg/LLaMA-LoRA-Tuner?
- A web UI and Colab notebook for fine-tuning LLaMA, GPT-J and similar models using LoRA, with a Gradio-based chat interface for demonstration.
- Is LLaMA-LoRA-Tuner open source?
- Yes — zetavg/LLaMA-LoRA-Tuner is an open-source project tracked on heatdrop.
- What language is LLaMA-LoRA-Tuner written in?
- zetavg/LLaMA-LoRA-Tuner is primarily written in Python.
- How popular is LLaMA-LoRA-Tuner?
- zetavg/LLaMA-LoRA-Tuner has 473 stars on GitHub.
- Where can I find LLaMA-LoRA-Tuner?
- zetavg/LLaMA-LoRA-Tuner is on GitHub at https://github.com/zetavg/LLaMA-LoRA-Tuner.