xAI Grok 1 weights out on Hugging Face! This repository contains the weights of the Grok-1 open-weights model. You can find the code in the GitHub Repository.
Here are the instructions for setting up and running the model:
- Start by cloning the repository and downloading the int8 checkpoint into the checkpoints directory. You can do this by opening your terminal, navigating to the directory where you want the repository to be, and executing the following commands:
git clone https://github.com/xai-org/grok-1.git
cd grok-1
pip install huggingface_hub[hf_transfer]
huggingface-cli download xai-org/grok-1 --repo-type model --include ckpt-0/* --local-dir checkpoints --local-dir-use-symlinks False- Once the above steps are complete, you can proceed to install the necessary requirements and run the model. Execute the following commands in the terminal while you’re still in the repository’s root directory:
pip install -r requirements.txt
python run.py- After running these commands, you should see the output from the language model on your terminal.
Please note, due to the model’s significant size (314 billion parameters), running the example code requires a machine equipped with multiple GPUs.
Read related articles: