Instructions to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B")
model = PeftModel.from_pretrained(base_model, "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1")

Transformers

How to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 with Transformers:

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

pipe = pipeline("text-generation", model="1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1

SGLang

How to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 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 "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1" \
    --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": "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1" \
        --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": "1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1 with Docker Model Runner:
```
docker model run hf.co/1jamesthompson1/Qwen3.5-9B-nz-wvs-sampled_response-cluster_1
```

Qwen3.5-9B-nz-wvs-sampled_response-cluster_1

File size: 2,055 Bytes

89868f7

{
  "Jinja2": "3.1.6",
  "MarkupSafe": "3.0.3",
  "PyYAML": "6.0.3",
  "Pygments": "2.20.0",
  "accelerate": "1.14.0",
  "aiohappyeyeballs": "2.7.1",
  "aiohttp": "3.14.3",
  "aiosignal": "1.4.0",
  "annotated-doc": "0.0.5",
  "anyio": "4.14.2",
  "attrs": "26.1.0",
  "bitsandbytes": "0.50.0",
  "certifi": "2026.7.22",
  "charset-normalizer": "3.4.9",
  "click": "8.4.2",
  "cuda-bindings": "13.3.1",
  "cuda-pathfinder": "1.6.0",
  "cuda-toolkit": "13.0.3.0",
  "datasets": "5.0.1",
  "dill": "0.4.1",
  "filelock": "3.32.0",
  "frozenlist": "1.8.0",
  "fsspec": "2026.6.0",
  "h11": "0.16.0",
  "hf-xet": "1.5.2",
  "httpcore": "1.0.9",
  "httpx": "0.28.1",
  "huggingface_hub": "1.25.1",
  "idna": "3.18",
  "markdown-it-py": "4.2.0",
  "mdurl": "0.1.2",
  "mpmath": "1.3.0",
  "multidict": "6.7.1",
  "multiprocess": "0.70.19",
  "networkx": "3.6.1",
  "numpy": "2.5.1",
  "nvidia-cublas": "13.1.1.3",
  "nvidia-cuda-cupti": "13.0.85",
  "nvidia-cuda-nvrtc": "13.0.88",
  "nvidia-cuda-runtime": "13.0.96",
  "nvidia-cudnn-cu13": "9.20.0.48",
  "nvidia-cufft": "12.0.0.61",
  "nvidia-cufile": "1.15.1.6",
  "nvidia-curand": "10.4.0.35",
  "nvidia-cusolver": "12.0.4.66",
  "nvidia-cusparse": "12.6.3.3",
  "nvidia-cusparselt-cu13": "0.8.1",
  "nvidia-nccl-cu13": "2.29.7",
  "nvidia-nvjitlink": "13.3.33",
  "nvidia-nvshmem-cu13": "3.4.5",
  "nvidia-nvtx": "13.0.85",
  "packaging": "26.2",
  "pandas": "3.0.5",
  "peft": "0.20.0",
  "pillow": "12.3.0",
  "propcache": "0.5.2",
  "psutil": "7.2.2",
  "pyarrow": "25.0.0",
  "python-dateutil": "2.9.0.post0",
  "python-dotenv": "1.2.2",
  "regex": "2026.7.19",
  "requests": "2.34.2",
  "rich": "15.0.0",
  "safetensors": "0.8.0",
  "setuptools": "83.0.0",
  "shellingham": "1.5.4",
  "six": "1.17.0",
  "sympy": "1.14.0",
  "tokenizers": "0.22.2",
  "torch": "2.13.0",
  "torchvision": "0.28.0",
  "tqdm": "4.70.0",
  "transformers": "5.14.1",
  "triton": "3.7.1",
  "trl": "1.9.2",
  "typer": "0.27.0",
  "typing_extensions": "4.16.0",
  "urllib3": "2.7.0",
  "xxhash": "3.8.1",
  "yarl": "1.24.5"
}