From c22c7dadcaa530d0def972bbad59a7ae26bb63a9 Mon Sep 17 00:00:00 2001
From: PENG Bo <33809201+BlinkDL@users.noreply.github.com>
Date: Wed, 14 Sep 2022 11:23:09 +0800
Subject: [PATCH] Update README.md

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

diff --git a/README.md b/README.md
index 817da1b..a148dbe 100644
--- a/README.md
+++ b/README.md
@@ -20,6 +20,8 @@ I am training RWKV-4 3B and 7B on the Pile (https://wandb.ai/blinkdl/RWKV-v4-Pil
 
 ![RWKV-v4-1.5B-Pile](RWKV-v4-1.5B-Pile.png)
 
+![RWKV-eval](RWKV-eval.png)
+
 All of the trained models will be open-source. Inference is very fast (only matrix-vector multiplications, no matrix-matrix multiplications) even on CPUs, so you can even run a LLM on your phone.
 
 How it works: RWKV gathers information to a number of channels, which are also decaying with different speeds as you move to the next token. It's very simple once you understand it.