Instructions to use Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM",
		"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/Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM

SGLang

How to use Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM 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 "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM" \
    --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": "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM",
		"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 "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM" \
        --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": "Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM with Docker Model Runner:
```
docker model run hf.co/Xingyu-Zheng/Qwopus3.5-27B-v3.5-INT8-FOEM
```

Note: The tool calling format in the chat_template has been set to Hermes format

by anyi28 - opened Apr 22

Discussion

anyi28

Apr 22

Therefore, when serving this model using vllm, you must specify --tool-call-parser=hermes for tool calls to be properly parsed, not qwen3_coder

Xingyu-Zheng

Owner Apr 24

Thank you very much for pointing this out. My primary expertise lies in model quantization algorithms, and I am not very familiar with the detailed configuration of vLLM deployment. If you notice any additional usage details or have feedback on your experience, please feel free to share them with me.

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