Instructions to use OpenGVLab/InternVL2-Llama3-76B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-Llama3-76B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-Llama3-76B", 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-Llama3-76B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenGVLab/InternVL2-Llama3-76B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-Llama3-76B"
# 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-Llama3-76B",
		"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-Llama3-76B

SGLang

How to use OpenGVLab/InternVL2-Llama3-76B 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-Llama3-76B" \
    --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-Llama3-76B",
		"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-Llama3-76B" \
        --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-Llama3-76B",
		"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-Llama3-76B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-Llama3-76B
```

czczup commited on Jul 17, 2024

Commit

c85e698

verified ·

1 Parent(s): d640123

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +18 -14

README.md CHANGED Viewed

@@ -68,13 +68,15 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va
 ### Video Benchmarks
-|      Benchmark       | GPT-4V | VILA-1.5 | LLaVA-NeXT-Video | InternVL2-40B | InternVL2-Llama3-76B |
-| :------------------: | :----: | :------: | :--------------: | :-----------: | :------------------: |
-|      Model Size      |   -    |   34B    |       34B        |      40B      |         76B          |
-|                      |        |          |                  |               |                      |
-|       MVBench        |   -    |    -     |        -         |     72.5      |         69.6         |
-| Video-MME<br>wo subs |  59.9  |   59.0   |       52.0       |     TODO      |         TODO         |
-| Video-MME<br>w/ subs |  63.3  |   59.4   |       54.9       |     TODO      |         TODO         |
 - We evaluate our models on MVBench by extracting 16 frames from each video, and each frame was resized to a 448x448 image.
@@ -486,13 +488,15 @@ InternVL 2.0 是一个多模态大语言模型系列，包含各种规模的模
 ### 视频相关评测
-|      评测数据集      | GPT-4V | VILA-1.5 | LLaVA-NeXT-Video | InternVL2-40B | InternVL2-Llama3-76B |
-| :------------------: | :----: | :------: | :--------------: | :-----------: | :------------------: |
-|       模型大小       |   -    |   34B    |       34B        |      40B      |         76B          |
-|                      |        |          |                  |               |                      |
-|       MVBench        |   -    |    -     |        -         |     72.5      |         69.6         |
-| Video-MME<br>wo subs |  59.9  |   59.0   |       52.0       |     TODO      |         TODO         |
-| Video-MME<br>w/ subs |  63.3  |   59.4   |       54.9       |     TODO      |         TODO         |
 - 我们通过从每个视频中提取16帧来评估我们的模型在MVBench上的性能，每个视频帧被调整为448x448的图像。

 ### Video Benchmarks
+|          Benchmark          | GPT-4V | VILA-1.5 | LLaVA-NeXT-Video | InternVL2-40B | InternVL2-Llama3-76B |
+| :-------------------------: | :----: | :------: | :--------------: | :-----------: | :------------------: |
+|         Model Size          |   -    |   34B    |       34B        |      40B      |         76B          |
+|                             |        |          |                  |               |                      |
+|           MVBench           |   -    |    -     |        -         |     72.5      |         69.6         |
+| MMBench-Video<sub>8f</sub>  |  1.53  |    -     |        -         |     1.32      |         1.37         |
+| MMBench-Video<sub>16f</sub> |  1.68  |    -     |        -         |     1.45      |         1.52         |
+|    Video-MME<br>wo subs     |  59.9  |   59.0   |       52.0       |     TODO      |         TODO         |
+|    Video-MME<br>w/ subs     |  63.3  |   59.4   |       54.9       |     TODO      |         TODO         |
 - We evaluate our models on MVBench by extracting 16 frames from each video, and each frame was resized to a 448x448 image.
 ### 视频相关评测
+|         评测数据集          | GPT-4V | VILA-1.5 | LLaVA-NeXT-Video | InternVL2-40B | InternVL2-Llama3-76B |
+| :-------------------------: | :----: | :------: | :--------------: | :-----------: | :------------------: |
+|          模型大小           |   -    |   34B    |       34B        |      40B      |         76B          |
+|                             |        |          |                  |               |                      |
+|           MVBench           |   -    |    -     |        -         |     72.5      |         69.6         |
+| MMBench-Video<sub>8f</sub>  |  1.53  |    -     |        -         |     1.32      |         1.37         |
+| MMBench-Video<sub>16f</sub> |  1.68  |    -     |        -         |     1.45      |         1.52         |
+|    Video-MME<br>wo subs     |  59.9  |   59.0   |       52.0       |     TODO      |         TODO         |
+|    Video-MME<br>w/ subs     |  63.3  |   59.4   |       54.9       |     TODO      |         TODO         |
 - 我们通过从每个视频中提取16帧来评估我们的模型在MVBench上的性能，每个视频帧被调整为448x448的图像。