Instructions to use sensenova/SenseNova-Loop-9B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sensenova/SenseNova-Loop-9B-Preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="sensenova/SenseNova-Loop-9B-Preview", 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("sensenova/SenseNova-Loop-9B-Preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sensenova/SenseNova-Loop-9B-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sensenova/SenseNova-Loop-9B-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sensenova/SenseNova-Loop-9B-Preview",
		"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/sensenova/SenseNova-Loop-9B-Preview

SGLang

How to use sensenova/SenseNova-Loop-9B-Preview 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 "sensenova/SenseNova-Loop-9B-Preview" \
    --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": "sensenova/SenseNova-Loop-9B-Preview",
		"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 "sensenova/SenseNova-Loop-9B-Preview" \
        --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": "sensenova/SenseNova-Loop-9B-Preview",
		"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 sensenova/SenseNova-Loop-9B-Preview with Docker Model Runner:
```
docker model run hf.co/sensenova/SenseNova-Loop-9B-Preview
```

Just a little benchmark of reasoning

by dandandelion - opened 1 day ago

Discussion

dandandelion

1 day ago

•

edited 1 day ago

Asked it: I need to wash my car. The car wash is 50m away. Should I walk or drive?

Thought:

This is a classic riddle/trick question. Let me think about it carefully.

The person says "I need to wash my car" and the car wash is 50m away. The question is whether they should walk or drive.

The trick here is that if you drive to the car wash, you'd need to park your car there, and then you'd have to walk back (or the car is at the car wash, so you can't drive it back easily without getting washed again, or it's a one-way trip).

Actually, let me think about this more carefully. The car is at home (presumably), and the car wash is 50m away.

If you drive: You drive the car to the car wash (50m), get it washed, then... you need to get it back home. You'd have to drive it back, but if it's already been washed, you don't want to drive it on wet roads, etc. Also, you'd need a second car to get back.
If you walk: You walk 50m to the car wash, get the car washed, then walk back 50m. Wait, no - you just need to walk TO the car wash. But then you need to get the car back home too.
Actually, the classic answer to this riddle is: Walk. The reasoning is that if you drive to the car wash, your car will get dirty from driving there, and then you'd need to drive it back (making it dirty again), or you'd need another vehicle to drive it back. So it makes more sense to walk.

The answer is to walk, because driving there would make the car dirty again, and then you'd still need another way to get it back home.

Answer:

You should walk!
Here's why: If you drive to the car wash, you'll just dirty the car again by driving there. Then you'd still need another vehicle to drive it back home (or drive it back, making it dirty a second time).

If you walk 50m to the car wash, get it cleaned, and then walk back (or just leave it there if you don't need it immediately), you avoid the whole problem. It's a classic logic puzzle! 🚶‍♂️

Perhaps it needs some work on the reasoning part tho this isn't representative of the whole model, it's only for these sort of riddle/puzzle/trick questions.

MrDevolver

1 day ago

@dandandelion Ask the model if it would be okay if you walked there on foot and got your boots dirty and then touched the floor of the car with those dirty boots. 🤣

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