Grok-1, the 314-billion-parameter Mixture of Experts (MoE) model open-sourced by Musk's xAI, is the largest open-source large language model, and allows for free distribution and commercialization of changes.
Grok-1 has attracted a lot of attention in the open source community since its release, and has been ranked No. 1 in the world on the GitHub Trending.
However, Grok-1 is built using Rust+JAX, which has a high threshold for users who are used to mainstream software ecosystems such as Python+PyTorch+HuggingFace to get started.
Colossal-AI team followed up immediately and provided an easy-to-use Python + PyTorch + HuggingFace version of Grok-1 for all AI developers.
Grok-1 greedy search test
HuggingFace Download:
Tutorial
Download the tokenizer from the official grok-1 repository.
wget https://github.com/xai-org/grok-1/raw/main/tokenizer.modelRun inference scripts
./run_inference_fast.sh hpcaitech/grok-1 tokenizer.modelModel weights will be downloaded and loaded automatically.
More details can be found in:
https://github.com/hpcaitech/ColossalAI/tree/main/examples/language/grok-1
Colossal-AI will further introduce optimizations for Grok-1 in parallel acceleration, quantitative reduction of cost, etc. in the near future. Welcome to stay tuned.
Colossal-AI open source address:
https://github.com/hpcaitech/ColossalAI
Comments