Upload folder using huggingface_hub

README.md

@@ -597,7 +597,7 @@ To deploy InternVL2 as an API, please configure the chat template config first.
 LMDeploy's `api_server` enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup:
 
 ```shell
-lmdeploy serve api_server OpenGVLab/InternVL2-40B --model-name InternVL2-40B --backend turbomind --server-port 23333 --chat-template chat_template.json
+lmdeploy serve api_server OpenGVLab/InternVL2-40B --backend turbomind --server-port 23333 --chat-template chat_template.json
 ```
 
 To use the OpenAI-style interface, you need to install OpenAI:
@@ -614,7 +614,7 @@ from openai import OpenAI
 client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
 model_name = client.models.list().data[0].id
 response = client.chat.completions.create(
-    model="InternVL2-40B",
+    model=model_name,
     messages=[{
         'role':
         'user',
@@ -644,7 +644,7 @@ TODO
 
 ## License
 
-This project is released under the MIT license, while InternLM is licensed under the Apache-2.0 license.
+This project is released under the MIT license, while InternLM2 is licensed under the Apache-2.0 license.
 
 ## Citation
 
@@ -893,7 +893,7 @@ print(sess.response.text)
 LMDeploy 的 `api_server` 使模型能够通过一个命令轻松打包成服务。提供的 RESTful API 与 OpenAI 的接口兼容。以下是服务启动的示例：
 
 ```shell
-lmdeploy serve api_server OpenGVLab/InternVL2-40B --model-name InternVL2-40B --backend turbomind --server-port 23333 --chat-template chat_template.json
+lmdeploy serve api_server OpenGVLab/InternVL2-40B --backend turbomind --server-port 23333 --chat-template chat_template.json
 ```
 
 为了使用OpenAI风格的API接口，您需要安装OpenAI:
@@ -910,7 +910,7 @@ from openai import OpenAI
 client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
 model_name = client.models.list().data[0].id
 response = client.chat.completions.create(
-    model="InternVL2-40B",
+    model=model_name,
     messages=[{
         'role':
         'user',