Instructions to use OpenGVLab/InternVL3-38B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3-38B-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-38B-hf")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OpenGVLab/InternVL3-38B-hf")
model = AutoModelForImageTextToText.from_pretrained("OpenGVLab/InternVL3-38B-hf")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3-38B-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3-38B-hf"
# 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/InternVL3-38B-hf",
		"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/InternVL3-38B-hf

SGLang

How to use OpenGVLab/InternVL3-38B-hf 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/InternVL3-38B-hf" \
    --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/InternVL3-38B-hf",
		"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/InternVL3-38B-hf" \
        --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/InternVL3-38B-hf",
		"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/InternVL3-38B-hf with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3-38B-hf
```

yonigozlan HF Staff commited on Apr 18, 2025

Commit

c098f52

verified ·

1 Parent(s): c4852ab

Upload InternVLForConditionalGeneration

Browse files

Files changed (19) hide show

config.json +1 -0
generation_config.json +6 -0
model-00001-of-00016.safetensors +3 -0
model-00002-of-00016.safetensors +3 -0
model-00003-of-00016.safetensors +3 -0
model-00004-of-00016.safetensors +3 -0
model-00005-of-00016.safetensors +3 -0
model-00006-of-00016.safetensors +3 -0
model-00007-of-00016.safetensors +3 -0
model-00008-of-00016.safetensors +3 -0
model-00009-of-00016.safetensors +3 -0
model-00010-of-00016.safetensors +3 -0
model-00011-of-00016.safetensors +3 -0
model-00012-of-00016.safetensors +3 -0
model-00013-of-00016.safetensors +3 -0
model-00014-of-00016.safetensors +3 -0
model-00015-of-00016.safetensors +3 -0
model-00016-of-00016.safetensors +3 -0
model.safetensors.index.json +0 -0

@@ -37,6 +37,7 @@
     "use_sliding_window": false,
     "vocab_size": 151674
   },
   "transformers_version": "4.52.0.dev0",
   "vision_config": {
     "architectures": [

     "use_sliding_window": false,
     "vocab_size": 151674
   },
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
   "vision_config": {
     "architectures": [

+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.52.0.dev0"
+}

+version https://git-lfs.github.com/spec/v1
+oid sha256:a77dfda0aafb9258be7fc631b56049d57b5f953ebd35196a6aa5b70061bdc510
+size 4988693808

+version https://git-lfs.github.com/spec/v1
+oid sha256:e55689b5e2a76724462140ab0c96b4b1e29f20940b56b36a4f3e590c9c5e0008
+size 4937410320

+version https://git-lfs.github.com/spec/v1
+oid sha256:906dc1df4cf30022138b2cabb2cf371a58aae3eda040ff4b725ca06309036779
+size 4960249904

+version https://git-lfs.github.com/spec/v1
+oid sha256:9460a70cc2fbe4006903303e300ec91ecb86be6fa19878679bf0596bcf5e7be6
+size 4876060256

+version https://git-lfs.github.com/spec/v1
+oid sha256:6687e857684d985fb44c200094edcac7f4a82b66bc812addc6462f4cd93fb4f4
+size 4876060272

+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3a4b62429ef86ad07b68475049fab91fa822226eae88ce8b02e53705eeeb31
+size 4876060312

+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfcc1e939bd52b6223255fc9fcbba66804878b8b0ed3841ffa856a1c5e352c5
+size 3377732008

	@@ -0,0 +1,6 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@