From 7c93e20c7e947c58999a4f969596f2306c7e5afd Mon Sep 17 00:00:00 2001
From: Muhammad Noraeii <Muhammad.Noraeii@gmail.com>
Date: Tue, 28 Jan 2025 01:02:19 +0330
Subject: [PATCH] Update README.md

Part chat model size updated
---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 7ecf87e..f6cc0dc 100644
--- a/README.md
+++ b/README.md
@@ -163,8 +163,8 @@ For developers looking to dive deeper, we recommend exploring [README_WEIGHTS.md
 
 Evaluation results on the ``Needle In A Haystack`` (NIAH) tests.  DeepSeek-V3 performs well across all context window lengths up to **128K**. 
 
-### Chat Model
-#### Standard Benchmarks (Models larger than 67B)
+## Chat Model
+### Standard Benchmarks (Models larger than 67B)
 <div align="center">
 
 | | **Benchmark (Metric)** | **DeepSeek V2-0506** | **DeepSeek V2.5-0905** | **Qwen2.5 72B-Inst.** | **Llama3.1 405B-Inst.** | **Claude-3.5-Sonnet-1022** | **GPT-4o 0513** | **DeepSeek V3** |