xAI has announced the release of the base model weights and network architecture of Grok-1, its extensive language model. This model is a 314 billion parameter Mixture-of-Experts model, entirely developed by xAI. The release corresponds to the raw base model checkpoint from the Grok-1 pre-training phase, which concluded in October 2023. It's important to note that the model has not been fine-tuned for any specific applications, like dialogues. The weights and architecture are offered under the Apache 2.0 license, promoting its use and modification to foster innovation. For those interested in starting to use the model, xAI provides detailed instructions in its GitHub repository.