From 5b690ebe4b23c1a16225623c3265c32a30860086 Mon Sep 17 00:00:00 2001
From: willieneis <willie.neiswanger@gmail.com>
Date: Wed, 29 May 2024 04:05:11 -0700
Subject: [PATCH] update README

---
 README.md | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index e886e1f..dc7f30e 100644
--- a/README.md
+++ b/README.md
@@ -1,11 +1,19 @@
-# k2_training
+# Training Code for LLM360 K2-65B
+
+This repository contains the code for training K2-65B, a 65 billion parameter large
+language model from LLM360.
+
+> [!NOTE]
+> This repository is under active development. If you have suggestions or find bugs, please open a GitHub issue or reach out.
 
 ### Launch Training
+To launch training, run:
 ```
 bash scripts/pretrain_65b.sh
 ```
 
 ### Converting Megatron Checkpoints to HuggingFace Format
+To convert model checkpoints from Megatron to HuggingFace format, run:
 ```
 python convert_ckpt_to_hf.py --load_path <megatron_ckpt_dir> --save_path <huggingface_ckpt_dir>
-```
\ No newline at end of file
+```