xai-org/grok-1
Grok open release
Backblaze Generative Media Hackathon
Build the next generation of AI media apps with Genblaze, stored on Backblaze B2. $10,000 in prizes.
Loading star history...
Use Cases & Benefits
- Grok-1 is a large-scale 314B parameter language model implemented in JAX, designed for advanced NLP tasks requiring extensive context handling.
- Key features include a Mixture of Experts architecture with 64 layers, rotary embeddings, activation sharding, 8-bit quantization, and support for long sequences up to 8192 tokens.
- The model requires significant GPU memory due to its size and has a less efficient MoE layer implementation to avoid custom kernels, which may limit performance optimization.
- With over 50,000 stars and 8,360 forks since March 2024, Grok-1 shows strong community interest and adoption in the open-source AI research space.
- Ideal for researchers and developers needing a state-of-the-art, open-weight large language model for experimentation, benchmarking, or integration into high-resource NLP applications.
About grok-1
Grok-1
This repository contains JAX example code for loading and running the Grok-1 open-weights model.
Make sure to download the checkpoint and place the ckpt-0 directory in checkpoints - see Downloading the weights
Then, run
pip install -r requirements.txt
python run.py
to test the code.
The script loads the checkpoint and samples from the model on a test input.
Due to the large size of the model (314B parameters), a machine with enough GPU memory is required to test the model with the example code. The implementation of the MoE layer in this repository is not efficient. The implementation was chosen to avoid the need for custom kernels to validate the correctness of the model.
Model Specifications
Grok-1 is currently designed with the following specifications:
- Parameters: 314B
- Architecture: Mixture of 8 Experts (MoE)
- Experts Utilization: 2 experts used per token
- Layers: 64
- Attention Heads: 48 for queries, 8 for keys/values
- Embedding Size: 6,144
- Tokenization: SentencePiece tokenizer with 131,072 tokens
- Additional Features:
- Rotary embeddings (RoPE)
- Supports activation sharding and 8-bit quantization
- Maximum Sequence Length (context): 8,192 tokens
Downloading the weights
You can download the weights using a torrent client and this magnet link:
magnet:?xt=urn:btih:5f96d43576e3d386c9ba65b883210a393b68210e&tr=https%3A%2F%2Facademictorrents.com%2Fannounce.php&tr=udp%3A%2F%2Ftracker.coppersurfer.tk%3A6969&tr=udp%3A%2F%2Ftracker.opentrackr.org%3A1337%2Fannounce
or directly using HuggingFace 🤗 Hub:
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
License
The code and associated Grok-1 weights in this release are licensed under the Apache 2.0 license. The license only applies to the source files in this repository and the model weights of Grok-1.
Discover Repositories
Search across tracked repositories by name or description