In this article, I’d like to put some interesting open source LLM code links.
From the star number change, we can have some interesting observations:
- Llama-cpp is more popular than the original Llama. Does this mean quite many people are checking the possibility of local deployment of the llama model although it is not allowed for commercial usage?
- The gpt4all attracts so many attention at the beginning of the release. Does this because it has a good name which contains gpt4?
An ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
Inference code for LLaMA models
Port of Facebook’s LLaMA model in C/C++
Code and documentation to train Stanford’s Alpaca models, and generate the data.
Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
If we want to check a more timely comparison, can check this Open LLM Leaderboard.