Instructions to use OpenGVLab/InternVL2-2B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-2B-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-2B-AWQ", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL2-2B-AWQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-2B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-2B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-2B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OpenGVLab/InternVL2-2B-AWQ

SGLang

How to use OpenGVLab/InternVL2-2B-AWQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenGVLab/InternVL2-2B-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-2B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenGVLab/InternVL2-2B-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL2-2B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OpenGVLab/InternVL2-2B-AWQ with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-2B-AWQ
```

cuierfei commited on Jul 29, 2024

Commit

a7311dd

verified ·

1 Parent(s): 5aa4844

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +6 -20
config.json +4 -1

README.md CHANGED Viewed

@@ -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.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))
 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.
 ```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
 ```
 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",
     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.
 ## Citation

 Trying the following codes, you can perform the batched offline inference with the quantized model:
 ```python
+from lmdeploy import pipeline, TurbomindEngineConfig
 from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-2B-AWQ'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
 backend_config = TurbomindEngineConfig(model_format='awq')
+pipe = pipeline(model, backend_config=backend_config, log_level='INFO')
 response = pipe(('describe this image', image))
 print(response.text)
 ```
 ### Service
+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 --backend turbomind --server-port 23333 --model-format awq
 ```
 To use the OpenAI-style interface, you need to install 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=model_name,
     messages=[{
         'role':
         'user',
 ## License
+This project is released under the MIT license, while InternLM2 is licensed under the Apache-2.0 license.
 ## Citation

config.json CHANGED Viewed

@@ -84,7 +84,10 @@
     "return_dict": true,
     "return_dict_in_generate": false,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
     "rope_theta": 1000000,
     "sep_token_id": null,
     "suppress_tokens": null,

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