Instructions to use tiny-random/sensenova-loop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/sensenova-loop with Transformers:

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

pipe = pipeline("image-text-to-text", model="tiny-random/sensenova-loop", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tiny-random/sensenova-loop", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/sensenova-loop with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/sensenova-loop"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/sensenova-loop",
		"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/tiny-random/sensenova-loop

SGLang

How to use tiny-random/sensenova-loop 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 "tiny-random/sensenova-loop" \
    --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": "tiny-random/sensenova-loop",
		"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 "tiny-random/sensenova-loop" \
        --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": "tiny-random/sensenova-loop",
		"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 tiny-random/sensenova-loop with Docker Model Runner:
```
docker model run hf.co/tiny-random/sensenova-loop
```

sensenova-loop / README.md

yujiepan

Upload folder using huggingface_hub

88cd4a6 verified 1 day ago

preview code

Raw History Blame Contribute Delete

4.24 kB

---
library_name: transformers
pipeline_tag: image-text-to-text
base_model:
- sensenova/SenseNova-Loop-9B-Preview
---
This is a randomly initialized tiny model based on [sensenova/SenseNova-Loop-9B-Preview](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) for testing and debugging.

| Feature | Source | This repo |
|---|---|---|
| Checkpoint tensor elements | 243.29M BF16, 9.41B F32 | 9.19K BF16, 4.55M F32 |
| Safetensors weight files | 38.14 GB (9 files) | 18.25 MB (2 files) |
| Distinct / executed decoder layers | 32 / 56 (block 4-28 twice) | 12 / 16 (block 4-7 twice) |
| Attention cadence | three linear then full, four-layer cycle | Same; four complete cycles |
| Hidden width / MLP width | 4,096 / 12,288 | 8 / 32 |
| Full Q heads / KV heads / head dim | 16 / 4 / 256 | 8 / 4 / 32 |
| Linear key/value heads x head dim | 16x128 / 32x128 | 4x32 / 8x32 |
| mHC streams / Sinkhorn iterations | 2 / 20 over layers 4-28 | 2 / 20 over layers 4-7 |
| MTP draft layers / precision | 1 / BF16 (separate mtp.safetensors) | Same |
| Vision depth / hidden / heads | 27 / 1,152 / 16 | 4 / 64 / 2 |
| Patch / temporal patch / spatial merge | 16 / 2 / 2 | Same |
| Vision position buffer | 2,304 entries | Same |
| Vocabulary rows / tying | 248,320 / untied | Same |
| Backbone storage precision | FP32 | Same |
| SSM/conv/mHC parameters | FP32 | Same |
| Maximum context length | 262,144 | Same |

The pinned Loop/mHC wrapper loads the native Qwen3.5 backbone; the shared block owns one weight set but one dynamic-cache slot per visit.

| File path | Size |
|------|------|
| model.safetensors | 18.2MB |
| mtp.safetensors | 0.0MB |

### Example usage

#### Transformers (unverified)

Load the included pinned Loop/mHC implementation with `trust_remote_code=True`. The example sends one image and four predecoded video frames; the hybrid linear-attention path requires CUDA.

```python
def run_transformers(model_id: str):
    import numpy as np
    import torch
    from PIL import Image
    from transformers import AutoModelForImageTextToText, AutoProcessor
    from transformers.video_utils import VideoMetadata
    model_id = str(model_id)
    processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
    model = (
        AutoModelForImageTextToText.from_pretrained(
            model_id, trust_remote_code=True, dtype=torch.bfloat16, attn_implementation="sdpa"
        )
        .eval()
        .cuda()
    )
    image = Image.fromarray(np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8), "RGB")
    frames = np.stack(
        [
            np.asarray(Image.new("RGB", (256, 256), color))
            for color in ((220, 30, 30), (30, 220, 30), (30, 30, 220), (220, 220, 30))
        ]
    )
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": image},
                {"type": "video", "video": frames},
                {"type": "text", "text": "Describe the image and the video."},
            ],
        }
    ]
    inputs = processor.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=True,
        return_dict=True,
        return_tensors="pt",
        enable_thinking=False,
        processor_kwargs={"video_metadata": [VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])]},
    ).to(model.device)
    assert inputs["pixel_values"].shape[0] > 0 and inputs["pixel_values_videos"].shape[0] > 0
    with torch.no_grad():
        logits = model(**inputs).logits
        assert torch.isfinite(logits).all()
        output = model.generate(**inputs, do_sample=False, min_new_tokens=8, max_new_tokens=8)
    print(processor.decode(output[0, inputs["input_ids"].shape[1] :], skip_special_tokens=False))
if __name__ == "__main__":
    run_transformers(model_id="scratch/sensenova-loop")
```

### Creating this repo

- Code: [.meta/create_model.py](.meta/create_model.py)
- Model structure: [.meta/model.log](.meta/model.log)
- Environment: [.meta/env.json](.meta/env.json)

### Change log

- 2026-11-03: Initial version: 12 physical layers / 16 looped executions with two-stream FP32 mHC routers and a separate BF16 MTP draft.

*This repo is generated by GPT-6.1-Sol.*

	---
	library_name: transformers
	pipeline_tag: image-text-to-text
	base_model:
	- sensenova/SenseNova-Loop-9B-Preview
	---

	This is a randomly initialized tiny model based on [sensenova/SenseNova-Loop-9B-Preview](https://huggingface.co/sensenova/SenseNova-Loop-9B-Preview) for testing and debugging.

	\| Feature \| Source \| This repo \|
	\|---\|---\|---\|
	\| Checkpoint tensor elements \| 243.29M BF16, 9.41B F32 \| 9.19K BF16, 4.55M F32 \|
	\| Safetensors weight files \| 38.14 GB (9 files) \| 18.25 MB (2 files) \|
	\| Distinct / executed decoder layers \| 32 / 56 (block 4-28 twice) \| 12 / 16 (block 4-7 twice) \|
	\| Attention cadence \| three linear then full, four-layer cycle \| Same; four complete cycles \|
	\| Hidden width / MLP width \| 4,096 / 12,288 \| 8 / 32 \|
	\| Full Q heads / KV heads / head dim \| 16 / 4 / 256 \| 8 / 4 / 32 \|
	\| Linear key/value heads x head dim \| 16x128 / 32x128 \| 4x32 / 8x32 \|
	\| mHC streams / Sinkhorn iterations \| 2 / 20 over layers 4-28 \| 2 / 20 over layers 4-7 \|
	\| MTP draft layers / precision \| 1 / BF16 (separate mtp.safetensors) \| Same \|
	\| Vision depth / hidden / heads \| 27 / 1,152 / 16 \| 4 / 64 / 2 \|
	\| Patch / temporal patch / spatial merge \| 16 / 2 / 2 \| Same \|
	\| Vision position buffer \| 2,304 entries \| Same \|
	\| Vocabulary rows / tying \| 248,320 / untied \| Same \|
	\| Backbone storage precision \| FP32 \| Same \|
	\| SSM/conv/mHC parameters \| FP32 \| Same \|
	\| Maximum context length \| 262,144 \| Same \|

	The pinned Loop/mHC wrapper loads the native Qwen3.5 backbone; the shared block owns one weight set but one dynamic-cache slot per visit.

	\| File path \| Size \|
	\|------\|------\|
	\| model.safetensors \| 18.2MB \|
	\| mtp.safetensors \| 0.0MB \|

	### Example usage

	#### Transformers (unverified)

	Load the included pinned Loop/mHC implementation with `trust_remote_code=True`. The example sends one image and four predecoded video frames; the hybrid linear-attention path requires CUDA.

	```python
	def run_transformers(model_id: str):
	import numpy as np
	import torch
	from PIL import Image
	from transformers import AutoModelForImageTextToText, AutoProcessor
	from transformers.video_utils import VideoMetadata

	model_id = str(model_id)
	processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
	model = (
	AutoModelForImageTextToText.from_pretrained(
	model_id, trust_remote_code=True, dtype=torch.bfloat16, attn_implementation="sdpa"
	)
	.eval()
	.cuda()
	)
	image = Image.fromarray(np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8), "RGB")
	frames = np.stack(
	[
	np.asarray(Image.new("RGB", (256, 256), color))
	for color in ((220, 30, 30), (30, 220, 30), (30, 30, 220), (220, 220, 30))
	]
	)
	messages = [
	{
	"role": "user",
	"content": [
	{"type": "image", "image": image},
	{"type": "video", "video": frames},
	{"type": "text", "text": "Describe the image and the video."},
	],
	}
	]
	inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
	enable_thinking=False,
	processor_kwargs={"video_metadata": [VideoMetadata(total_num_frames=4, fps=2, frames_indices=[0, 1, 2, 3])]},
	).to(model.device)
	assert inputs["pixel_values"].shape[0] > 0 and inputs["pixel_values_videos"].shape[0] > 0
	with torch.no_grad():
	logits = model(**inputs).logits
	assert torch.isfinite(logits).all()
	output = model.generate(**inputs, do_sample=False, min_new_tokens=8, max_new_tokens=8)
	print(processor.decode(output[0, inputs["input_ids"].shape[1] :], skip_special_tokens=False))


	if __name__ == "__main__":
	run_transformers(model_id="scratch/sensenova-loop")
	```

	### Creating this repo

	- Code: [.meta/create_model.py](.meta/create_model.py)
	- Model structure: [.meta/model.log](.meta/model.log)
	- Environment: [.meta/env.json](.meta/env.json)

	### Change log

	- 2026-11-03: Initial version: 12 physical layers / 16 looped executions with two-stream FP32 mHC routers and a separate BF16 MTP draft.

	This repo is generated by GPT-6.1-Sol.