Instructions to use OpenGVLab/InternVL2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-1B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-1B", 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/InternVL2-1B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-1B"
# 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/InternVL2-1B",
		"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/InternVL2-1B

SGLang

How to use OpenGVLab/InternVL2-1B 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/InternVL2-1B" \
    --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/InternVL2-1B",
		"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/InternVL2-1B" \
        --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/InternVL2-1B",
		"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/InternVL2-1B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-1B
```

Compatibility with v5

#10

by RaushanTurganbay HF Staff - opened Mar 16

base: refs/heads/main

←

from: refs/pr/10

Discussion Files changed

-1

Files changed (1) hide show

modeling_intern_vit.py +3 -1

modeling_intern_vit.py CHANGED Viewed

@@ -4,6 +4,7 @@
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
 from typing import Optional, Tuple, Union
 import torch
@@ -309,7 +310,7 @@ class InternVisionEncoder(nn.Module):
         super().__init__()
         self.config = config
         # stochastic depth decay rule
-        dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
         self.layers = nn.ModuleList([
             InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
         self.gradient_checkpointing = True
@@ -374,6 +375,7 @@ class InternVisionModel(PreTrainedModel):
         self.embeddings = InternVisionEmbeddings(config)
         self.encoder = InternVisionEncoder(config)
     def resize_pos_embeddings(self, old_size, new_size, patch_size):
         pos_emb = self.embeddings.position_embedding

 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
+import numpy as np
 from typing import Optional, Tuple, Union
 import torch
         super().__init__()
         self.config = config
         # stochastic depth decay rule
+        dpr = [x for x in BrokenPipeError.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
         self.layers = nn.ModuleList([
             InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
         self.gradient_checkpointing = True
         self.embeddings = InternVisionEmbeddings(config)
         self.encoder = InternVisionEncoder(config)
+        self.post_init()
     def resize_pos_embeddings(self, old_size, new_size, patch_size):
         pos_emb = self.embeddings.position_embedding