Instructions to use OpenGVLab/InternVL3-14B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3-14B-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-14B-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/InternVL3-14B-hf")
model = AutoModelForImageTextToText.from_pretrained("OpenGVLab/InternVL3-14B-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/InternVL3-14B-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3-14B-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/InternVL3-14B-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/InternVL3-14B-hf

SGLang

How to use OpenGVLab/InternVL3-14B-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/InternVL3-14B-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/InternVL3-14B-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/InternVL3-14B-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/InternVL3-14B-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/InternVL3-14B-hf with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3-14B-hf
```

yonigozlan HF Staff commited on Apr 18, 2025

Commit

e661acf

verified ·

1 Parent(s): 456a941

Upload processor

Browse files

Files changed (4) hide show

preprocessor_config.json +1 -0
processor_config.json +9 -0
special_tokens_map.json +9 -63
tokenizer_config.json +1 -0

preprocessor_config.json CHANGED Viewed

@@ -23,6 +23,7 @@
   "input_data_format": null,
   "max_patches": 12,
   "min_patches": 1,
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "return_tensors": null,

   "input_data_format": null,
   "max_patches": 12,
   "min_patches": 1,
+  "processor_class": "InternVLProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "return_tensors": null,

processor_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "context_image_token": "<IMG_CONTEXT>",
+  "end_image_token": "</img>",
+  "fake_image_token": "<image>",
+  "fake_video_token": "<video>",
+  "image_seq_length": 256,
+  "processor_class": "InternVLProcessor",
+  "start_image_token": "<img>"
+}

special_tokens_map.json CHANGED Viewed

@@ -13,69 +13,15 @@
     "<|vision_pad|>",
     "<|image_pad|>",
     "<|video_pad|>",
-    {
-      "content": "<img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<IMG_CONTEXT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
   ],
   "eos_token": {
     "content": "<|im_end|>",

     "<|vision_pad|>",
     "<|image_pad|>",
     "<|video_pad|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
   ],
   "eos_token": {
     "content": "<|im_end|>",

tokenizer_config.json CHANGED Viewed

@@ -282,6 +282,7 @@
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|endoftext|>",
   "return_token_type_ids": false,
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|endoftext|>",
+  "processor_class": "InternVLProcessor",
   "return_token_type_ids": false,
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",