yangjianxin1/Firefly
Open-source LLM training toolkit supporting pre-training, instruction fine-tuning, and DPO across multiple model architectures.
Not currently ranked — collecting fresh signals.
star history
Firefly is a one-stop large model training tool that supports full-parameter training, LoRA, and QLoRA efficient training methods. It supports pre-training, supervised fine-tuning (SFT), and Direct Preference Optimization (DPO) across a wide range of open-source LLMs including Qwen, Yi, Llama, Gemma, MiniCPM, InternLM, and others. The project integrates with Unsloth for accelerated training and reduced memory usage, and provides configuration-based training for easy model switching.
Frequently asked
- What is yangjianxin1/Firefly?
- Open-source LLM training toolkit supporting pre-training, instruction fine-tuning, and DPO across multiple model architectures.
- Is Firefly open source?
- Yes — yangjianxin1/Firefly is an open-source project tracked on heatdrop.
- What language is Firefly written in?
- yangjianxin1/Firefly is primarily written in Python.
- How popular is Firefly?
- yangjianxin1/Firefly has 6.6k stars on GitHub.
- Where can I find Firefly?
- yangjianxin1/Firefly is on GitHub at https://github.com/yangjianxin1/Firefly.