Open source implementation for LLaMA-based ChatGPT training process

Meta has recently released LLaMA, a collection of foundational large language models ranging from 7 to 65 billion parameters. LLaMA is creating a lot of excitement because it is smaller than GPT-3 but has better performance. For example, LLaMA's 13B architecture outperforms GPT-3 despite being 10 times smaller. This new collection of fundamental models opens the door to faster inference performance and chatGPT-like real-time assistants, while being cost-effective and running on a single GPU.

However, LLaMA was not fine-tuned for instruction task with a Reinforcement Learning from Human Feedback (RLHF) training process.

The good news is that we introduce ChatLLaMA, the first open source implementation of RLHF process that leverages LLaMA:

- A complete open source implementation that enables you to build a ChatGPT-style service based on pre-trained LLaMA models.
- Compared to the original ChatGPT, the training process and single-GPU inference are much faster and cheaper by taking advantage of the smaller size of LLaMA architectures.
- ChatLLaMA has built-in support for DeepSpeed ZERO to speedup the fine-tuning process.
- The library also supports all LLaMA model architectures (7B, 13B, 33B, 65B), so that you can fine-tune the model according to your preferences for training time and inference performance.

If you like the project, please show your support by leaving a star ⭐.