Update README.md

README.md

@@ -19,7 +19,8 @@ Tiger Research is a futuristic research lab under Tigerobo, dedicated to applyin
 |                   | v3 [[huggingface]](https://huggingface.co/TigerResearch/tigerbot-70b-chat-v3)[[modelscope](https://modelscope.cn/models/TigerResearch/tigerbot-70b-chat-v3/summary)] | llama-2      | 129           | From tigerbot-70b-base v1  |
 |                   | v2 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-v2)][[modelscope](https://modelscope.cn/models/TigerResearch/tigerbot-70b-chat-v2/summary)] | llama-2      | 129           | From tigerbot-70b-base v1  |
 |                   | v1 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-v1)] | llama-2      | 129           | From tigerbot-70b-base v1  |
-| tigerbot-70b-chat-4bit | v3 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-4bit-exl2)] | llama-2      | 37           | From tigerbot-70b-chat v3|
+| tigerbot-70b-chat-4bit | v4 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-v4-4bit-exl2)] | llama-2      | 37           | From tigerbot-70b-chat v4|
+|                        | v3 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-v3-4bit-exl2)] | llama-2      | 37           | From tigerbot-70b-chat v3|
 |                        | v2 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-4bit-v2)] | llama-2      | 37           | From tigerbot-70b-chat v2|
 |                        | v1 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-70b-chat-4bit-v1)] | llama-2      | 37           | From tigerbot-70b-chat v1|
 | tigerbot-13b-base | v3 [[huggingface](https://huggingface.co/TigerResearch/tigerbot-13b-base-v3)][[modelscope](https://modelscope.cn/models/TigerResearch/tigerbot-13b-base-v3/summary)] | llama-2      | 26.6           | From llama-2-13b weights  |