Instructions to use sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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": "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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/sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4

SGLang

How to use sakamakismile/Huihui-Qwen3.6-27B-abliterated-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 "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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": "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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 "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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": "sakamakismile/Huihui-Qwen3.6-27B-abliterated-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 sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4 with Docker Model Runner:
```
docker model run hf.co/sakamakismile/Huihui-Qwen3.6-27B-abliterated-NVFP4
```

--quantization modelopt 不支持

by jack-zhuhua - opened Jul 9

Discussion

jack-zhuhua

Jul 9

•

edited Jul 9

(APIServer pid=53) INFO 07-09 03:45:40 [nixl_utils.py:20] Setting UCX_RCACHE_MAX_UNRELEASED to '1024' to avoid a rare memory leak in UCX when using NIXL.
(APIServer pid=53) INFO 07-09 03:45:40 [nixl_utils.py:32] NIXL is available
(APIServer pid=53) INFO 07-09 03:45:40 [model.py:554] Resolved architecture: Qwen3_5ForConditionalGeneration
(APIServer pid=53) INFO 07-09 03:45:40 [model.py:1685] Using max model len 131072

(APIServer pid=53) Traceback (most recent call last):
(APIServer pid=53) File "/usr/local/bin/vllm", line 10, in
(APIServer pid=53) sys.exit(main())
(APIServer pid=53) ^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/main.py", line 75, in main
(APIServer pid=53) args.dispatch_function(args)
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/serve.py", line 122, in cmd
(APIServer pid=53) uvloop.run(run_server(args))
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/uvloop/init.py", line 96, in run
(APIServer pid=53) return __asyncio.run(
(APIServer pid=53) ^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/lib/python3.12/asyncio/runners.py", line 195, in run
(APIServer pid=53) return runner.run(main)
(APIServer pid=53) ^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
(APIServer pid=53) return self._loop.run_until_complete(task)
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/uvloop/init.py", line 48, in wrapper
(APIServer pid=53) return await main
(APIServer pid=53) ^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 678, in run_server
(APIServer pid=53) await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 692, in run_server_worker
(APIServer pid=53) async with build_async_engine_client(
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter
(APIServer pid=53) return await anext(self.gen)
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 100, in build_async_engine_client
(APIServer pid=53) async with build_async_engine_client_from_engine_args(
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/lib/python3.12/contextlib.py", line 210, in aenter
(APIServer pid=53) return await anext(self.gen)
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/api_server.py", line 124, in build_async_engine_client_from_engine_args
(APIServer pid=53) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1600, in create_engine_config
(APIServer pid=53) model_config = self.create_model_config()
(APIServer pid=53) ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1448, in create_model_config
(APIServer pid=53) return ModelConfig(
(APIServer pid=53) ^^^^^^^^^^^^
(APIServer pid=53) File "/usr/local/lib/python3.12/dist-packages/pydantic/_internal/_dataclasses.py", line 121, in init
(APIServer pid=53) s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=53) pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=53) Value error, Quantization method specified in the model config (compressed-tensors) does not match the quantization method specified in the quantization argument (modelopt). [type=value_error, input_value=ArgsKwargs((), {'model': ...nderer_num_workers': 1}), input_type=ArgsKwargs]
(APIServer pid=53) For further information visit https://errors.pydantic.dev/2.13/v/value_error

start command:
--quantization modelopt
--trust-remote-code
--reasoning-parser qwen3
--enable-auto-tool-choice
--tool-call-parser qwen3_xml
--default-chat-template-kwargs '{"preserve_thinking":true}'
--enable-prefix-caching
--enable-chunked-prefill
--max-model-len 131072
--gpu-memory-utilization 0.5
--kv-cache-dtype fp8_e4m3
2>&1 | tee /workspace/logs/vllm-main.log

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