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

Libraries

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

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-2B", 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", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-2B"
# 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",
		"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

SGLang

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

czczup commited on Aug 23, 2024

Commit

2baab50

verified ·

1 Parent(s): addb5d4

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +1 -1
modeling_internvl_chat.py +3 -1

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 license: mit
 pipeline_tag: image-text-to-text
 library_name: transformers
-base_model:
   - OpenGVLab/InternViT-300M-448px
   - internlm/internlm2-chat-1_8b
 base_model_relation: merge

 license: mit
 pipeline_tag: image-text-to-text
 library_name: transformers
+base_model:
   - OpenGVLab/InternViT-300M-448px
   - internlm/internlm2-chat-1_8b
 base_model_relation: merge

modeling_internvl_chat.py CHANGED Viewed

@@ -38,7 +38,7 @@ class InternVLChatModel(PreTrainedModel):
     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
-    def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
         assert version_cmp(transformers.__version__, '4.36.2', 'ge')
@@ -50,6 +50,8 @@ class InternVLChatModel(PreTrainedModel):
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
         self.ps_version = config.ps_version
         logger.info(f'num_image_token: {self.num_image_token}')
         logger.info(f'ps_version: {self.ps_version}')

     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
+    def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
         super().__init__(config)
         assert version_cmp(transformers.__version__, '4.36.2', 'ge')
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
         self.ps_version = config.ps_version
+        config.vision_config.use_flash_attn = True if use_flash_attn else False
+        config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'
         logger.info(f'num_image_token: {self.num_image_token}')
         logger.info(f'ps_version: {self.ps_version}')