Instructions to use OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF", 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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF", 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?"}
        ]
    },
]
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_5-GPT-OSS-20B-A4B-Preview-HF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-HF

SGLang

How to use OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-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_5-GPT-OSS-20B-A4B-Preview-HF with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF
```

image_token_id mismatch causes "Image features and image tokens do not match" error in OSS-20B model

by juno-kai - opened Aug 30, 2025

Discussion

juno-kai

Aug 30, 2025

•

edited Aug 30, 2025

Issue Description

When using the OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF model, inference fails with the following error:
-> ValueError: Image features and image tokens do not match: tokens: 0, features 3328

Root Cause

The issue stems from a token ID mismatch between the model configuration and the tokenizer:

The model's config.json specifies "image_token_id": 151671
However, the OSS-20B tokenizer actually maps <IMG_CONTEXT> to token ID 200021 (as seen in tokenizer_config.json)
The 14B model uses 151671 for <IMG_CONTEXT> (in its added_tokens.json), which appears to have been carried over to the OSS-20B config

Workaround

Users can fix this by manually updating the image_token_id after loading the model:

model = AutoModelForImageTextToText.from_pretrained(model_name, ...)
model.config.image_token_id = 200021  # Correct token ID for OSS-20B

Suggested Fix

Update the model's config.json to use the correct image_token_id: 200021 to match the tokenizer configuration.

Additional Note

The OSS-20B model is missing the added_tokens.json file that exists in the 14B model, though this doesn't appear to cause issues as the tokens are defined in tokenizer_config.json.

Weiyun1025

OpenGVLab org Aug 31, 2025

🤗 Thank you for your interest and for pointing out the hidden bug as well as providing a detailed analysis. I have already updated the model’s config and verified that it now runs successfully.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment