Merge 4a368c2c73 into 7050ed204b

The `cuda12-pip` package was wrongly named `cuda12_pip`
in requirements.txt

.gitignore

@@ -0,0 +1,2 @@
+checkpoints/*
+!checkpoints/README.md

README.md

@@ -2,28 +2,60 @@
 
 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`.
-Then, run
+Make sure to download the checkpoint and place the `ckpt-0` directory in `checkpoints` - see [Downloading the weights](#downloading-the-weights)
 
-```shell
+## 1. Installation
+
+1. Install the project dependencies
+
+```bash
 pip install -r requirements.txt
+```
+
+2. Run the project
+
+```bash
 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.
+Due to the large size of the model (314 Billion 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.
 
-# Downloading the weights
+## 2. 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
+- **TPU/GPU:** NVIDIA/AMD supported only
+
+## 3. 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

requirements.txt

@@ -1,4 +1,4 @@
-dm_haiku==0.0.12
-jax[cuda12_pip]==0.4.25 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
+dm-haiku==0.0.12
+jax[cuda12-pip]==0.4.25 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
 numpy==1.26.4
 sentencepiece==0.2.0