fla-org/flame
๐ฅ A minimal training framework for scaling FLA models
- Stars
- 424
- Forks
- 71
- Open issues
- 2
- Last push
- 6mo ago
About flame
flame is a free, open-source LLM chat app by fla-org, written mainly in Python. ๐ฅ A minimal training framework for scaling FLA models. It has 424 GitHub stars and 71 forks, and was last updated 6mo ago. It's released under the MIT license, a standard open-source license.
- License
- MIT
- Language
- Python
- Stars
- 424
- Last update
- 6mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Yes
Similar free tools
Hands-On-Large-Language-Models30k stars ยท Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Qwen22k stars ยท The official repo of Qwen (้ไนๅ้ฎ) chat & pretrained large language model proposed by Alibaba Cloud.
flash-linear-attention6.0k stars ยท ๐ Efficient implementations for emerging model architectures
FinGPT21k stars ยท FinGPT: Open-Source Financial Large Language Models! Revolutionize ๐ฅ We release the trained model on HuggingFace.
Megatron-LM18k stars ยท Ongoing research training transformer models at scale
langextract39k stars ยท A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
flame FAQ
Is flame free?
Yes. flame is open source and free to use. It's released under the MIT license, a standard open-source license.
Does flame run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does flame need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is flame still maintained?
It was last updated 6mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to flame?
Similar free, open-source tools include Hands-On-Large-Language-Models, Qwen, flash-linear-attention, FinGPT.