Merge remote-tracking branch 'origin/main' into add-ipfs

This commit is contained in:
AveryanAlex 2024-03-18 20:45:31 +03:00
commit ac5ee50129
No known key found for this signature in database
GPG Key ID: 3C23C7BD99452036

View File

@ -2,7 +2,8 @@
This repository contains JAX example code for loading and running the Grok-1 open-weights model. This repository contains JAX example code for loading and running the Grok-1 open-weights model.
Make sure to download the checkpoint and place `ckpt-0` directory in `checkpoint`. Make sure to download the checkpoint and place the `ckpt-0` directory in `checkpoints` - see [Downloading the weights](#downloading-the-weights)
Then, run Then, run
```shell ```shell
@ -17,18 +18,42 @@ 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. 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. 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 # Downloading the weights
You can download the weights using a torrent client and this magnet link: 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 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 using IPFS CID (blake3): using IPFS CID (blake3):
``` ```
bafyb4id5xdepghz5pvplhylgz7scjkoefh4d34j4kdw2w5hzrblv3uwbw4 bafyb4id5xdepghz5pvplhylgz7scjkoefh4d34j4kdw2w5hzrblv3uwbw4
``` ```
or directly using HuggingFace:
```
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 # License
The code and associated Grok-1 weights in this release are licensed under the The code and associated Grok-1 weights in this release are licensed under the