Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/xai-org/grok-1
Grok open release
https://github.com/xai-org/grok-1
Last synced: 1 day ago
JSON representation
Grok open release
- Host: GitHub
- URL: https://github.com/xai-org/grok-1
- Owner: xai-org
- License: apache-2.0
- Created: 2024-03-17T08:53:38.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-08-30T04:17:25.000Z (6 months ago)
- Last Synced: 2025-02-03T19:45:38.980Z (8 days ago)
- Language: Python
- Size: 984 KB
- Stars: 49,884
- Watchers: 603
- Forks: 8,341
- Open Issues: 109
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
- awesome-vision-language-pretraining - [github - os) [[twitter post]](https://twitter.com/danielhanchen/status/1769550950270910630) (Miscellaneous)
- StarryDivineSky - xai-org/grok-1 - 1开源权重模型的JAX示例代码，Grok-1是一个拥有3140亿参数的混合专家模型(MoE)，每个token使用2个专家，模型包含64层，查询注意力头48个，键/值注意力头8个，嵌入大小为6144，使用SentencePiece分词器，支持旋转嵌入(RoPE)、激活分片和8比特量化，最大序列长度为8192个token。模型权重可通过磁力链接或HuggingFace Hub下载，代码和模型权重均采用Apache 2.0许可证。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- awesome-latest-LLM - Grok-1
- Awesome-AITools - Github - org/grok-1?style=social)|免费| (精选文章 / 开源大语言模型)
- awesome-repositories - xai-org/grok-1 - Grok open release (Python)
- my-awesome - xai-org/grok-1 - 08 star:49.9k fork:8.3k Grok open release (Python)
- AiTreasureBox - xai-org/grok-1 - 02-07_49887_0](https://img.shields.io/github/stars/xai-org/grok-1.svg)|Grok open release| (Repos)
- awesome-llm-and-aigc - Grok-1 - org/grok-1?style=social"/> : This repository contains JAX example code for loading and running the Grok-1 open-weights model. (Summary)
- awesome-llm-and-aigc - Grok-1 - org/grok-1?style=social"/> : This repository contains JAX example code for loading and running the Grok-1 open-weights model. (Summary)
README
# 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](#downloading-the-weights)
Then, run
```shell
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](https://huggingface.co/xai-org/grok-1):
```
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.