Instructions to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="gitcommit90/SenseNova-Loop-9B-Preview-NVFP4", 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("gitcommit90/SenseNova-Loop-9B-Preview-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4",
		"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/gitcommit90/SenseNova-Loop-9B-Preview-NVFP4

SGLang

How to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 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 "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4" \
    --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": "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4",
		"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 "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4" \
        --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": "gitcommit90/SenseNova-Loop-9B-Preview-NVFP4",
		"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 gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with Docker Model Runner:
```
docker model run hf.co/gitcommit90/SenseNova-Loop-9B-Preview-NVFP4
```

SenseNova-Loop-9B-Preview-NVFP4 / evaluation /compare_vs_ref.json

gitcommit90

NVFP4 (ModelOpt) quantization of sensenova/SenseNova-Loop-9B-Preview @27abea77 with BF16 MTP head

a57aa9f verified 1 day ago

Raw History Blame Contribute Delete

3.21 kB

{
  "ref": "eval/runs/sglang_bf16",
  "cand": "eval/runs/sglang_nvfp4_v1",
  "tasks": {
    "gsm8k": {
      "n": 80,
      "ref_acc": 0.925,
      "cand_acc": 0.95,
      "delta": 0.025,
      "delta_boot95": [
        -0.025,
        0.075
      ],
      "ref_only_correct": 1,
      "cand_only_correct": 3,
      "mcnemar_p": 0.625,
      "ref_agreement": 0.9375,
      "identical_output": 0.075,
      "mean_tokens_ref": 191.5,
      "mean_tokens_cand": 187.2,
      "truncated_ref": 1,
      "truncated_cand": 1,
      "errors_cand": 0
    },
    "humaneval": {
      "n": 40,
      "ref_acc": 0.825,
      "cand_acc": 0.8,
      "delta": -0.025,
      "delta_boot95": [
        -0.075,
        0.0
      ],
      "ref_only_correct": 1,
      "cand_only_correct": 0,
      "mcnemar_p": 1.0,
      "ref_agreement": 0.425,
      "identical_output": 0.375,
      "mean_tokens_ref": 226.6,
      "mean_tokens_cand": 198.0,
      "truncated_ref": 0,
      "truncated_cand": 0,
      "errors_cand": 0
    },
    "ifeval": {
      "n": 60,
      "ref_acc": 0.7833333333333333,
      "cand_acc": 0.75,
      "delta": -0.03333333333333333,
      "delta_boot95": [
        -0.13333333333333333,
        0.06666666666666667
      ],
      "ref_only_correct": 6,
      "cand_only_correct": 4,
      "mcnemar_p": 0.75390625,
      "ref_agreement": 0.05,
      "identical_output": 0.05,
      "mean_tokens_ref": 318.9,
      "mean_tokens_cand": 272.7,
      "truncated_ref": 5,
      "truncated_cand": 4,
      "errors_cand": 0
    },
    "mmlu_pro": {
      "n": 60,
      "ref_acc": 0.65,
      "cand_acc": 0.6833333333333333,
      "delta": 0.03333333333333333,
      "delta_boot95": [
        -0.06666666666666667,
        0.13333333333333333
      ],
      "ref_only_correct": 4,
      "cand_only_correct": 6,
      "mcnemar_p": 0.75390625,
      "ref_agreement": 0.7666666666666667,
      "identical_output": 0.0,
      "mean_tokens_ref": 622.1,
      "mean_tokens_cand": 588.5,
      "truncated_ref": 13,
      "truncated_cand": 9,
      "errors_cand": 0
    },
    "tools": {
      "n": 20,
      "ref_acc": 0.95,
      "cand_acc": 0.95,
      "delta": 0.0,
      "delta_boot95": [
        -0.15,
        0.15
      ],
      "ref_only_correct": 1,
      "cand_only_correct": 1,
      "mcnemar_p": 1.0,
      "ref_agreement": 0.85,
      "identical_output": 0.0,
      "mean_tokens_ref": 64.2,
      "mean_tokens_cand": 54.3,
      "truncated_ref": 0,
      "truncated_cand": 0,
      "errors_cand": 0
    },
    "vqa": {
      "n": 40,
      "ref_acc": 0.9,
      "cand_acc": 0.9,
      "delta": 0.0,
      "delta_boot95": [
        -0.075,
        0.075
      ],
      "ref_only_correct": 1,
      "cand_only_correct": 1,
      "mcnemar_p": 1.0,
      "ref_agreement": 0.925,
      "identical_output": 0.925,
      "mean_tokens_ref": 4.1,
      "mean_tokens_cand": 4.1,
      "truncated_ref": 0,
      "truncated_cand": 0,
      "errors_cand": 0
    }
  },
  "overall_micro": {
    "n": 300,
    "ref_acc": 0.8266666666666667,
    "cand_acc": 0.83,
    "delta": 0.0033333333333333335,
    "delta_boot95": [
      -0.03,
      0.04
    ],
    "ref_agreement": 0.65,
    "identical_output": 0.20333333333333334
  }
}

	{
	"ref": "eval/runs/sglang_bf16",
	"cand": "eval/runs/sglang_nvfp4_v1",
	"tasks": {
	"gsm8k": {
	"n": 80,
	"ref_acc": 0.925,
	"cand_acc": 0.95,
	"delta": 0.025,
	"delta_boot95": [
	-0.025,
	0.075
	],
	"ref_only_correct": 1,
	"cand_only_correct": 3,
	"mcnemar_p": 0.625,
	"ref_agreement": 0.9375,
	"identical_output": 0.075,
	"mean_tokens_ref": 191.5,
	"mean_tokens_cand": 187.2,
	"truncated_ref": 1,
	"truncated_cand": 1,
	"errors_cand": 0
	},
	"humaneval": {
	"n": 40,
	"ref_acc": 0.825,
	"cand_acc": 0.8,
	"delta": -0.025,
	"delta_boot95": [
	-0.075,
	0.0
	],
	"ref_only_correct": 1,
	"cand_only_correct": 0,
	"mcnemar_p": 1.0,
	"ref_agreement": 0.425,
	"identical_output": 0.375,
	"mean_tokens_ref": 226.6,
	"mean_tokens_cand": 198.0,
	"truncated_ref": 0,
	"truncated_cand": 0,
	"errors_cand": 0
	},
	"ifeval": {
	"n": 60,
	"ref_acc": 0.7833333333333333,
	"cand_acc": 0.75,
	"delta": -0.03333333333333333,
	"delta_boot95": [
	-0.13333333333333333,
	0.06666666666666667
	],
	"ref_only_correct": 6,
	"cand_only_correct": 4,
	"mcnemar_p": 0.75390625,
	"ref_agreement": 0.05,
	"identical_output": 0.05,
	"mean_tokens_ref": 318.9,
	"mean_tokens_cand": 272.7,
	"truncated_ref": 5,
	"truncated_cand": 4,
	"errors_cand": 0
	},
	"mmlu_pro": {
	"n": 60,
	"ref_acc": 0.65,
	"cand_acc": 0.6833333333333333,
	"delta": 0.03333333333333333,
	"delta_boot95": [
	-0.06666666666666667,
	0.13333333333333333
	],
	"ref_only_correct": 4,
	"cand_only_correct": 6,
	"mcnemar_p": 0.75390625,
	"ref_agreement": 0.7666666666666667,
	"identical_output": 0.0,
	"mean_tokens_ref": 622.1,
	"mean_tokens_cand": 588.5,
	"truncated_ref": 13,
	"truncated_cand": 9,
	"errors_cand": 0
	},
	"tools": {
	"n": 20,
	"ref_acc": 0.95,
	"cand_acc": 0.95,
	"delta": 0.0,
	"delta_boot95": [
	-0.15,
	0.15
	],
	"ref_only_correct": 1,
	"cand_only_correct": 1,
	"mcnemar_p": 1.0,
	"ref_agreement": 0.85,
	"identical_output": 0.0,
	"mean_tokens_ref": 64.2,
	"mean_tokens_cand": 54.3,
	"truncated_ref": 0,
	"truncated_cand": 0,
	"errors_cand": 0
	},
	"vqa": {
	"n": 40,
	"ref_acc": 0.9,
	"cand_acc": 0.9,
	"delta": 0.0,
	"delta_boot95": [
	-0.075,
	0.075
	],
	"ref_only_correct": 1,
	"cand_only_correct": 1,
	"mcnemar_p": 1.0,
	"ref_agreement": 0.925,
	"identical_output": 0.925,
	"mean_tokens_ref": 4.1,
	"mean_tokens_cand": 4.1,
	"truncated_ref": 0,
	"truncated_cand": 0,
	"errors_cand": 0
	}
	},
	"overall_micro": {
	"n": 300,
	"ref_acc": 0.8266666666666667,
	"cand_acc": 0.83,
	"delta": 0.0033333333333333335,
	"delta_boot95": [
	-0.03,
	0.04
	],
	"ref_agreement": 0.65,
	"identical_output": 0.20333333333333334
	}
	}