From 638602753732a6c39c89a99a2c1d5b1b99bd8a41 Mon Sep 17 00:00:00 2001
From: Sami Jaghouar <sami.jaghouar@hotmail.fr>
Date: Tue, 12 Nov 2024 06:24:11 +0000
Subject: [PATCH] update readme

---
 README.md | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index c1129b2e..c8b670f4 100644
--- a/README.md
+++ b/README.md
@@ -38,14 +38,20 @@ A research paper about the framework and our INTELLECT-1 10B experiment is comin
 
 ## Getting Started
 
-1. Install `uv`:
+1. Clone: 
+
+```bash
+git clone git@github.com:PrimeIntellect-ai/prime.git
+```
+
+2. Install `uv`:
 
 ```bash
 curl -LsSf https://astral.sh/uv/install.sh | sh
 source $HOME/.local/bin/env
 ```
 
-2. Set up the environment:
+3. Set up the environment:
 ```bash
 sudo apt install iperf -y
 uv venv
@@ -55,12 +61,27 @@ uv pip install flash-attn --no-build-isolation
 git submodule update --init --recursive
 ```
 
-3. Log into Hugging Face:
-prime uses gated models tokenizers [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1), [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) and pulls the [C4:en](https://huggingface.co/datasets/allenai/c4) dataset subset. It is required to request access to the models then log into Hugging Face with a read token to begin training.
+
+4. Log into Hugging Face:
 ```bash
 huggingface-cli login
 ```
 
+all steps:
+
+```
+git clone git@github.com:PrimeIntellect-ai/prime.git
+cd prime
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source $HOME/.local/bin/env
+sudo apt install iperf -y
+uv venv
+source .venv/bin/activate
+uv sync --extra all
+uv pip install flash-attn --no-build-isolation
+git submodule update --init --recursive
+```
+
 
 ### Quick Check