From 94b3882d307b9e63f959ac5d3dbb389278de8823 Mon Sep 17 00:00:00 2001
From: josc146 <josStorer@outlook.com>
Date: Fri, 29 Dec 2023 12:26:33 +0800
Subject: [PATCH] release v1.6.7

---
 CURRENT_CHANGE.md | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/CURRENT_CHANGE.md b/CURRENT_CHANGE.md
index b1ae4a0e..72e814d8 100644
--- a/CURRENT_CHANGE.md
+++ b/CURRENT_CHANGE.md
@@ -1,12 +1,10 @@
 ## Changes
 
-- improve refreshRemoteModels
-- reduce precompiled web_rwkv_py size
-- webgpu(Python) max_buffer_size (12B support) and turbo
-- improve role-playing effect
-- update manifest.json (a lot of new models)
-- bump webgpu(ai00_server) mode to v0.3.8
-- improve details
+- rwkv5 lora finetune support (https://github.com/JL-er/RWKV-v5-lora)
+- improve memory usage and speed of convert_safetensors.py
+- webgpu(python) state cache support
+- improve state cache performance (especially for rwkv.cpp)
+- chore
 
 ## Install