Upload folder using huggingface_hub

README.md

@@ -47,17 +47,13 @@ This article comprises the following sections:
 Trying the following codes, you can perform the batched offline inference with the quantized model:
 
 ```python
-from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
+from lmdeploy import pipeline, TurbomindEngineConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2-2B-AWQ'
-system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室及多家合作单位联合开发的多模态大语言模型。'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-chat_template_config = ChatTemplateConfig('internvl-internlm2')
-chat_template_config.meta_instruction = system_prompt
 backend_config = TurbomindEngineConfig(model_format='awq')
-pipe = pipeline(model, chat_template_config=chat_template_config,
-                backend_config=backend_config))
+pipe = pipeline(model, backend_config=backend_config, log_level='INFO')
 response = pipe(('describe this image', image))
 print(response.text)
 ```
@@ -66,20 +62,10 @@ For more information about the pipeline parameters, please refer to [here](https
 
 ### Service
 
-To deploy InternVL2 as an API, please configure the chat template config first. Create the following JSON file `chat_template.json`.
-
-```json
-{
-    "model_name":"internvl-internlm2",
-    "meta_instruction":"我是书生·万象，英文名是InternVL，是由上海人工智能实验室及多家合作单位联合开发的多模态大语言模型。",
-    "stop_words":["<|im_start|>", "<|im_end|>"]
-}
-```
-
-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.
+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/InternVL2-2B-AWQ --model-name InternVL2-2B-AWQ --backend turbomind --server-port 23333 --model-format awq --chat-template chat_template.json
+lmdeploy serve api_server OpenGVLab/InternVL2-2B-AWQ --backend turbomind --server-port 23333 --model-format awq
 ```
 
 To use the OpenAI-style interface, you need to install OpenAI:
@@ -96,7 +82,7 @@ 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="InternVL2-2B-AWQ",
+    model=model_name,
     messages=[{
         'role':
         'user',
@@ -118,7 +104,7 @@ print(response)
 
 ## 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
 

config.json

@@ -84,7 +84,10 @@
     "return_dict": true,
     "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
+    "rope_scaling": {
+      "factor": 2.0,
+      "type": "dynamic"
+    },
     "rope_theta": 1000000,
     "sep_token_id": null,
     "suppress_tokens": null,