Instructions to use AvaXiao/ReToken-InternVL3.5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AvaXiao/ReToken-InternVL3.5-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="AvaXiao/ReToken-InternVL3.5-8B", 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("AvaXiao/ReToken-InternVL3.5-8B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AvaXiao/ReToken-InternVL3.5-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AvaXiao/ReToken-InternVL3.5-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AvaXiao/ReToken-InternVL3.5-8B",
		"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/AvaXiao/ReToken-InternVL3.5-8B

SGLang

How to use AvaXiao/ReToken-InternVL3.5-8B 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 "AvaXiao/ReToken-InternVL3.5-8B" \
    --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": "AvaXiao/ReToken-InternVL3.5-8B",
		"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 "AvaXiao/ReToken-InternVL3.5-8B" \
        --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": "AvaXiao/ReToken-InternVL3.5-8B",
		"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 AvaXiao/ReToken-InternVL3.5-8B with Docker Model Runner:
```
docker model run hf.co/AvaXiao/ReToken-InternVL3.5-8B
```

AvaXiao

nielsr HF Staff commited on 24 days ago

Commit

2b8ad0f

1 Parent(s): 2f2860c

Add model card (#1)

Browse files

- Add model card (d818507aea618620d69bf39f4d5fe22fa10b3c68)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +13 -0

README.md ADDED Viewed

	@@ -0,0 +1,13 @@

+---
+license: mit
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
+# ReToken: One Token to Improve Vision–Language Models for Visual Retrieval
+This repository contains the model from the paper [ReToken: One Token to Improve Vision-Language Models for Visual Retrieval](https://huggingface.co/papers/2607.28627).
+**ReToken** is a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache.
+Code: https://github.com/avaxiao/ReToken