update huggingface internlm-chat-7b model url (#546)

README.md

@@ -109,7 +109,7 @@ pip install lmdeploy
 
 # Make sure you have git-lfs installed (https://git-lfs.com)
 git lfs install
-git clone https://huggingface.co/internlm/internlm-chat-7b /path/to/internlm-chat-7b
+git clone https://huggingface.co/internlm/internlm-chat-7b-v1_1 /path/to/internlm-chat-7b
 
 # if you want to clone without large files – just their pointers
 # prepend your git clone with the following env var:

README_zh-CN.md

@@ -110,7 +110,7 @@ pip install lmdeploy
 
 # Make sure you have git-lfs installed (https://git-lfs.com)
 git lfs install
-git clone https://huggingface.co/internlm/internlm-chat-7b /path/to/internlm-chat-7b
+git clone https://huggingface.co/internlm/internlm-chat-7b-v1_1 /path/to/internlm-chat-7b
 
 # if you want to clone without large files – just their pointers
 # prepend your git clone with the following env var:

docs/en/kv_int8.md

@@ -69,7 +69,7 @@ python3 -m lmdeploy.turbomind.chat ./workspace
 
 ## GPU Memory Test
 
-The test object is the [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) model.
+The test object is the [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b-v1_1) model.
 Testing method:
 
 1. Use `deploy.py` to convert the model, modify the maximum concurrency in the `workspace` configuration; adjust the number of requests in `llama_config.ini`.
@@ -93,7 +93,7 @@ As can be seen, the fp16 version requires 1030MB of GPU memory for each concurre
 
 ## Accuracy Test
 
-The test object is the [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) command model.
+The test object is the [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b-v1_1) command model.
 
 Below is the result of PTQ quantization of `kCacheKVInt8` method with only 128 randomly selected data from the c4 dataset. The accuracy was tested using [opencompass](https://github.com/InternLM/opencompass) before and after quantization.
 

docs/zh_cn/kv_int8.md

@@ -69,7 +69,7 @@ python3 -m lmdeploy.turbomind.chat ./workspace
 
 ## 显存测试
 
-测试对象为 [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) 模型。
+测试对象为 [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b-v1_1) 模型。
 测试方法：
 
 1. 使用 `deploy.py` 转换模型，修改 `workspace` 配置中的最大并发数；调整 `llama_config.ini` 中的请求数
@@ -93,7 +93,7 @@ python3 -m lmdeploy.turbomind.chat ./workspace
 
 ## 精度测试
 
-测试对象为 [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b) 指令模型。
+测试对象为 [internlm-chat-7b](https://huggingface.co/internlm/internlm-chat-7b-v1_1) 指令模型。
 
 以下是 `kCacheKVInt8` 方法仅从 c4 数据集，随机选择 128 条数据 PTQ 量化。量化前后均使用 [opencompass](https://github.com/InternLM/opencompass) 测试精度。