Image-Text-to-Text
Transformers
Safetensors
qwen3_vl
qwen3-vl
viss
streaming-video
visual-question-answering
causal-video
conversational
Instructions to use mis2/ViSS-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mis2/ViSS-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="mis2/ViSS-8B") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mis2/ViSS-8B") model = AutoModelForMultimodalLM.from_pretrained("mis2/ViSS-8B", device_map="auto") 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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mis2/ViSS-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mis2/ViSS-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": "mis2/ViSS-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/mis2/ViSS-8B
- SGLang
How to use mis2/ViSS-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 "mis2/ViSS-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": "mis2/ViSS-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 "mis2/ViSS-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": "mis2/ViSS-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 mis2/ViSS-8B with Docker Model Runner:
docker model run hf.co/mis2/ViSS-8B
Download code/scripts/configure_evaluation_protocol.py from mis2/ViSS-8B: direct link, hf CLI and curl.
- Browser
- Download file 2.05 kB
-
https://huggingface.co/mis2/ViSS-8B/resolve/main/code/scripts/configure_evaluation_protocol.py
- Command line
-
hf download hf://mis2/ViSS-8B/code/scripts/configure_evaluation_protocol.py
-
curl -L -o configure_evaluation_protocol.py https://huggingface.co/mis2/ViSS-8B/resolve/main/code/scripts/configure_evaluation_protocol.py
2.05 kB
| """Bind the public protocol template to the user's own evaluation assets.""" | |
| from __future__ import annotations | |
| import argparse | |
| import json | |
| from pathlib import Path | |
| from experiments.evaluate_qwen3vl_recent4_full import ( | |
| sha256_file, | |
| validate_processor_contract, | |
| ) | |
| def configure( | |
| *, | |
| template: Path, | |
| streaming_samples: Path, | |
| ovo_samples: Path, | |
| processor_config: Path, | |
| output: Path, | |
| ) -> None: | |
| protocol = json.loads(template.read_text(encoding="utf-8")) | |
| for benchmark, path in ( | |
| ("streamingbench", streaming_samples), | |
| ("ovo", ovo_samples), | |
| ): | |
| path = path.resolve(strict=True) | |
| protocol["benchmarks"][benchmark]["export"] = str(path) | |
| protocol["benchmarks"][benchmark]["export_sha256"] = sha256_file(path) | |
| processor_config = processor_config.resolve(strict=True) | |
| if processor_config.name != "preprocessor_config.json": | |
| raise ValueError("Pass the processor's preprocessor_config.json") | |
| protocol["inference"]["processor_contract"]["preprocessor_config_sha256"] = ( | |
| sha256_file(processor_config) | |
| ) | |
| validate_processor_contract(processor_config.parent, protocol) | |
| protocol["status"] = "locked" | |
| output.parent.mkdir(parents=True, exist_ok=True) | |
| with output.open("x", encoding="utf-8") as handle: | |
| json.dump(protocol, handle, indent=2) | |
| handle.write("\n") | |
| def main() -> None: | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument( | |
| "--template", | |
| type=Path, | |
| default=Path("configs/evaluation/recent4.example.json"), | |
| ) | |
| parser.add_argument("--streaming-samples", type=Path, required=True) | |
| parser.add_argument("--ovo-samples", type=Path, required=True) | |
| parser.add_argument("--processor-config", type=Path, required=True) | |
| parser.add_argument("--output", type=Path, required=True) | |
| args = parser.parse_args() | |
| configure(**vars(args)) | |
| print(f"Created local evaluation protocol: {args.output}") | |
| if __name__ == "__main__": | |
| main() | |