From 81969b0a0671a881cd1356d4a8ffc8c62b954fc1 Mon Sep 17 00:00:00 2001
From: Afueth Thomas <97304915+Afueth@users.noreply.github.com>
Date: Mon, 27 Jan 2025 15:11:49 +0530
Subject: [PATCH] Update README.md

Updated the introductory sentence in the "Introduction" section to improve clarity and readability.

Changed:
"We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token."

To: "DeepSeek-V3 is a powerful Mixture-of-Experts (MoE) language model with 671 billion total parameters, of which 37 billion are activated per token."

This revision ensures conciseness and better emphasis on key details.
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 7ecf87e..39a2c0f 100644
--- a/README.md
+++ b/README.md
@@ -47,7 +47,7 @@
 
 ## 1. Introduction
 
-We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. 
+DeepSeek-V3 is a powerful Mixture-of-Experts (MoE) language model with 671 billion total parameters, of which 37 billion are activated per token. 
 To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. 
 Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. 
 We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities.