https://github.com/jazelly/finetunellms
Easy and Fast LLM finetuning on GPU or CPU.
https://github.com/jazelly/finetunellms
finetune llama llm lora train typescript webui
Last synced: 6 months ago
JSON representation
Easy and Fast LLM finetuning on GPU or CPU.
- Host: GitHub
- URL: https://github.com/jazelly/finetunellms
- Owner: jazelly
- License: mit
- Created: 2024-04-20T03:52:09.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-23T11:42:52.000Z (7 months ago)
- Last Synced: 2025-04-14T07:08:28.075Z (6 months ago)
- Topics: finetune, llama, llm, lora, train, typescript, webui
- Language: TypeScript
- Homepage:
- Size: 8.02 MB
- Stars: 35
- Watchers: 4
- Forks: 10
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# FinetuneLLMs (Work in Progress, Actively! 🔥)
Finetune an LLM, within a few clicks!
## How to run
The best way to do this is via docker,
```
docker compose up -d
```
In browser, visit `http://localhost:8080`
For detailed explanation on the structure, see [BUILD.md](./BUILD.md)
## 🔥Goal & Roadmap🔥
The main objective of this project is to lower the barrier to training large language models, especially for startup companies that have hardware in hands.
Roadmap
## Contributing
Thank you very very much for your contributions. You can follow the
[contribution guide](CONTRIBUTING.md) to get started.