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 / runtime-v2 /bench /prof_drive.py

gitcommit90

Publish runtime v2 optimization, final comparisons and figures (weights unchanged)

8edc128 verified about 24 hours ago

Raw History Blame Contribute Delete

1.32 kB

"""Drive a short torch-profiler capture: warmup, then start_profile(num_steps) + N concurrent requests."""
import sys, time, json, threading, requests
sys.path.insert(0, "/home/tux/sensenova-loop-nvfp4/eval")
from perf_bench import build_prompt_text
base = "http://127.0.0.1:30080"
conc = int(sys.argv[1]); steps = int(sys.argv[2]); prefix = sys.argv[3]
text, _, _ = build_prompt_text(1024, "/home/tux/sensenova-loop-nvfp4/upstream/SenseNova-Loop-9B-Preview/tokenizer.json")
def req(i, n=64):
    r = requests.post(base + "/v1/chat/completions", json={"model": "x", "messages": [{"role": "user", "content": f"[{time.time()}-{i}] " + text}],
        "max_tokens": n, "min_tokens": n, "ignore_eos": True, "temperature": 0, "chat_template_kwargs": {"enable_thinking": False}}, timeout=600)
    return r.json()["usage"]
print("warm", req(-1, 32))
ths = [threading.Thread(target=req, args=(i, 600)) for i in range(conc)]
for t in ths: t.start()
time.sleep(2.0 + 0.5 * conc)  # past prefill, into decode
r = requests.post(base + "/start_profile", json={"num_steps": steps, "activities": ["CPU", "GPU"], "profile_prefix": prefix})
print("profile", r.status_code, r.text[:200])
for t in ths: t.join()
print(json.dumps(requests.get(base + "/get_server_info").json().get("internal_states", [{}])[0].get("avg_spec_accept_length")))

	"""Drive a short torch-profiler capture: warmup, then start_profile(num_steps) + N concurrent requests."""
	import sys, time, json, threading, requests
	sys.path.insert(0, "/home/tux/sensenova-loop-nvfp4/eval")
	from perf_bench import build_prompt_text
	base = "http://127.0.0.1:30080"
	conc = int(sys.argv[1]); steps = int(sys.argv[2]); prefix = sys.argv[3]
	text, _, _ = build_prompt_text(1024, "/home/tux/sensenova-loop-nvfp4/upstream/SenseNova-Loop-9B-Preview/tokenizer.json")
	def req(i, n=64):
	r = requests.post(base + "/v1/chat/completions", json={"model": "x", "messages": [{"role": "user", "content": f"[{time.time()}-{i}] " + text}],
	"max_tokens": n, "min_tokens": n, "ignore_eos": True, "temperature": 0, "chat_template_kwargs": {"enable_thinking": False}}, timeout=600)
	return r.json()["usage"]
	print("warm", req(-1, 32))
	ths = [threading.Thread(target=req, args=(i, 600)) for i in range(conc)]
	for t in ths: t.start()
	time.sleep(2.0 + 0.5 * conc) # past prefill, into decode
	r = requests.post(base + "/start_profile", json={"num_steps": steps, "activities": ["CPU", "GPU"], "profile_prefix": prefix})
	print("profile", r.status_code, r.text[:200])
	for t in ths: t.join()
	print(json.dumps(requests.get(base + "/get_server_info").json().get("internal_states", [{}])[0].get("avg_spec_accept_length")))