Instructions to use mis2/ViSS-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

ViSS-8B

File size: 2,530 Bytes

78ac017

{
  "format": "iclr_video.locked_evaluation_protocol.v1",
  "protocol_id": "recent4_full_v1",
  "status": "template",
  "applies_to": "all baseline and candidate checkpoints",
  "inference": {
    "causal_prefix_only": true,
    "sampling_fps": 1.0,
    "context_policy": "recent_n",
    "recent_frames": 4,
    "timestamp_rule": "match the SimpleStream release: decode a four-second half-open causal prefix window [max(0,t-4),t) at nominal 1 FPS and retain exactly four independently encoded image frames; only prefixes shorter than two raw frames repeat frame zero",
    "allow_future_frames": false,
    "allow_global_frames": false,
    "allow_extra_frame_inspection": false,
    "allow_persistent_visual_or_text_memory": false,
    "visual_input_mode": "four independent image frames using qwen-vl-utils fetch_video (image_patch_size=14), never Qwen video tokens",
    "processor_contract": {
      "preprocessor_config_sha256": "",
      "image_processor_type": "Qwen2VLImageProcessorFast",
      "patch_size": 16,
      "merge_size": 2,
      "temporal_patch_size": 2,
      "shortest_edge": 65536,
      "longest_edge": 16777216,
      "reference_visual_tokens_per_frame": 576,
      "reason": "Bind the processor used by your evaluation before inference."
    },
    "prompt_source": "StreamingBench SimpleStream release MCQ template; OVO backward/realtime SimpleStream release one-letter template; OVO forward frozen official task wrapper; no system message",
    "decode": {
      "do_sample": false,
      "temperature": 0.0
    }
  },
  "benchmarks": {
    "streamingbench": {
      "scope": "Real-Time full",
      "export": "data/streamingbench/queries.jsonl",
      "export_sha256": "",
      "expected_queries": 2495,
      "expected_groups": {
        "real_time_visual": 2495
      },
      "primary_metric": "official Real-Time accuracy"
    },
    "ovo": {
      "scope": "all 12 tasks: Real-Time, Backward, and Forward",
      "export": "data/ovo/queries.jsonl",
      "export_sha256": "",
      "expected_queries": 3035,
      "expected_tasks": {
        "ACR": 109,
        "ASI": 148,
        "ATR": 116,
        "CRR": 240,
        "EPM": 297,
        "FPD": 101,
        "HLD": 186,
        "OCR": 149,
        "OJR": 184,
        "REC": 698,
        "SSR": 629,
        "STU": 178
      },
      "primary_metric": "official Total Avg",
      "secondary_metrics": [
        "micro Overall",
        "Real-Time Avg",
        "Backward Avg",
        "Forward Avg",
        "RT/BT Avg"
      ]
    }
  }
}