Instructions to use OpenGVLab/InternVL2-40B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-40B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-40B", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL2-40B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenGVLab/InternVL2-40B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-40B"
# 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/InternVL2-40B",
		"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/InternVL2-40B

SGLang

How to use OpenGVLab/InternVL2-40B 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/InternVL2-40B" \
    --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/InternVL2-40B",
		"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/InternVL2-40B" \
        --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/InternVL2-40B",
		"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/InternVL2-40B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-40B
```

czczup commited on Dec 8, 2024

Commit

79c0c57

verified ·

1 Parent(s): fc807c9

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -11

README.md CHANGED Viewed

@@ -115,7 +115,7 @@ Limitations: Although we have made efforts to ensure the safety of the model dur
 ## Quick Start
-We provide an example code to run InternVL2-40B using `transformers`.
 > Please use transformers>=4.37.2 to ensure the model works normally.
@@ -150,10 +150,6 @@ model = AutoModel.from_pretrained(
     trust_remote_code=True).eval()
 ```
-#### BNB 4-bit Quantization
-> **⚠️ Warning:** Due to significant quantization errors with BNB 4-bit quantization on InternViT-6B, the model may produce nonsensical outputs and fail to understand images. Therefore, please avoid using BNB 4-bit quantization.
 #### Multiple GPUs
 The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors.
@@ -443,7 +439,7 @@ response, history = model.chat(tokenizer, pixel_values, question, generation_con
                                num_patches_list=num_patches_list, history=None, return_history=True)
 print(f'User: {question}\nAssistant: {response}')
-question = 'Describe this video in detail. Don\'t repeat.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list, history=history, return_history=True)
 print(f'User: {question}\nAssistant: {response}')
@@ -502,7 +498,7 @@ from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-40B'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
 response = pipe(('describe this image', image))
 print(response.text)
 ```
@@ -521,7 +517,7 @@ from lmdeploy.vl import load_image
 from lmdeploy.vl.constants import IMAGE_TOKEN
 model = 'OpenGVLab/InternVL2-40B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
 image_urls=[
     'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
@@ -543,7 +539,7 @@ from lmdeploy import pipeline, TurbomindEngineConfig
 from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-40B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
 image_urls=[
     "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
@@ -563,7 +559,7 @@ from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
 from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-40B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
 gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
@@ -578,7 +574,7 @@ print(sess.response.text)
 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 --backend turbomind --server-port 23333
 ```
 To use the OpenAI-style interface, you need to install OpenAI:

 ## Quick Start
+We provide an example code to run `InternVL2-40B` using `transformers`.
 > Please use transformers>=4.37.2 to ensure the model works normally.
     trust_remote_code=True).eval()
 ```
 #### Multiple GPUs
 The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors.
                                num_patches_list=num_patches_list, history=None, return_history=True)
 print(f'User: {question}\nAssistant: {response}')
+question = 'Describe this video in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list, history=history, return_history=True)
 print(f'User: {question}\nAssistant: {response}')
 model = 'OpenGVLab/InternVL2-40B'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 response = pipe(('describe this image', image))
 print(response.text)
 ```
 from lmdeploy.vl.constants import IMAGE_TOKEN
 model = 'OpenGVLab/InternVL2-40B'
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 image_urls=[
     'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
 from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-40B'
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 image_urls=[
     "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
 from lmdeploy.vl import load_image
 model = 'OpenGVLab/InternVL2-40B'
+pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192, tp=2))
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
 gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
 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 --backend turbomind --server-port 23333 --tp 2
 ```
 To use the OpenAI-style interface, you need to install OpenAI: