update readme.

b4rtaz · Jun 1, 2024 · ecdadee · ecdadee
1 parent a5e0445
commit ecdadee
Show file tree

Hide file tree

Showing 3 changed files with 0 additions and 22 deletions.
diff --git a/README.md b/README.md
@@ -116,7 +116,6 @@ All tests below were conducted on c3d-highcpu-30 (30 vCPU, 15 core, 59 GB memory
 
 * [How to Run Llama 2](./docs/LLAMA.md#how-to-run-llama-2)
 * [How to Run Llama 3](./docs/LLAMA.md#how-to-run-llama-3)
-* [How to Run Grok-1](./docs/GROK.md)
 
 ## 📟 How to Run on Raspberry Pi Devices
 

diff --git a/docs/GROK.md b/docs/GROK.md
diff --git a/docs/LLAMA.md b/docs/LLAMA.md
@@ -37,8 +37,6 @@ In the table below, you can find the expected size of the converted weights with
 
 ## How to Run Llama 3
 
-You can skip the 1 - 9 points by downloading the converted Llama 3 8B Q40 model from [here](https://huggingface.co/b4rtaz/llama-3-8b-distributed-llama).
-
 1. Get an access to the model on [Llama 3 website](https://llama.meta.com/llama-downloads).
 2. Clone the `https://github.com/meta-llama/llama3` repository.
 3. Run the `download.sh` script to download the model.