Home

Awesome

ChatLLaMA

📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

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 LLaMA based on RLHF:

<img width="1032" alt="Screen Shot 2023-02-26 at 10 56 13 PM" src="https://user-images.githubusercontent.com/83510798/221439813-5972d029-dae5-4561-ab3d-5a55fa5cde09.png">

Image from OpenAI’s blog.

Installation

pip install chatllama

Get started with ChatLLaMA

:warning: Please note this code represents the algorithmic implementation for RLHF training process of LLaMA and does not contain the model weights. To access the model weights, you need to apply to Meta's form.

ChatLLaMA allows you to easily train LLaMA-based architectures in a similar way to ChatGPT, using RLHF. For example, below is the code to start the training in the case of ChatLLaMA 7B.

from chatllama.rlhf.trainer import RLTrainer
from chatllama.rlhf.config import Config

path = "path_to_config_file.yaml"
config = Config(path=path)
trainer = RLTrainer(config.trainer)
trainer.distillate()
trainer.train()
trainer.training_stats.plot()

Note that you should provide Meta's original weights and your custom dataset before starting the fine-tuning process. Alternatively, you can generate your own dataset using LangChain's agents.

python generate_dataset.py

The code is originally from nebuly-ai with some changes. More changes will follow up soon. And the original license link is here.