Instructions to use lxcxjxhx/Qwen3.5-0.8B-HOS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lxcxjxhx/Qwen3.5-0.8B-HOS with Transformers:

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

pipe = pipeline("image-text-to-text", model="lxcxjxhx/Qwen3.5-0.8B-HOS")
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("lxcxjxhx/Qwen3.5-0.8B-HOS")
model = AutoModelForMultimodalLM.from_pretrained("lxcxjxhx/Qwen3.5-0.8B-HOS", 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 lxcxjxhx/Qwen3.5-0.8B-HOS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lxcxjxhx/Qwen3.5-0.8B-HOS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lxcxjxhx/Qwen3.5-0.8B-HOS",
		"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/lxcxjxhx/Qwen3.5-0.8B-HOS

SGLang

How to use lxcxjxhx/Qwen3.5-0.8B-HOS 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 "lxcxjxhx/Qwen3.5-0.8B-HOS" \
    --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": "lxcxjxhx/Qwen3.5-0.8B-HOS",
		"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 "lxcxjxhx/Qwen3.5-0.8B-HOS" \
        --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": "lxcxjxhx/Qwen3.5-0.8B-HOS",
		"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 lxcxjxhx/Qwen3.5-0.8B-HOS with Docker Model Runner:
```
docker model run hf.co/lxcxjxhx/Qwen3.5-0.8B-HOS
```

Qwen3.5-0.8B-HOS / scripts /prepare_data.sh

lxcxjxhx

Upload folder using huggingface_hub

70771b6 verified 2 months ago

Raw

History Blame Contribute Delete

2.38 kB

	#!/bin/bash
	# 数据下载与清洗脚本
	# 适用于 Qwen3.5-0.8B-HOS 训练流程

	set -e

	echo "============================================"
	echo " 准备训练数据集"
	echo "============================================"

	# 数据集目录
	DATA_DIR="datasets"
	mkdir -p "$DATA_DIR"

	# 从 HuggingFace 下载数据集
	echo "[1/4] 下载数据集..."
	python -c "
	from datasets import load_dataset
	from huggingface_hub import hf_hub_download
	import os

	# 下载 infosec-dataset-training 数据集
	print('下载 cybersecurity_hq...')
	ds = load_dataset('lxcxjxhx/infosec-dataset-training', 'cybersecurity_hq')
	ds['train'].to_json(os.path.join('$DATA_DIR', 'cybersecurity_hq.jsonl'), orient='records', lines=True, force_ascii=False)

	print('下载 cybersecurity_sharegpt...')
	ds = load_dataset('lxcxjxhx/infosec-dataset-training', 'cybersecurity_sharegpt')
	ds['train'].to_json(os.path.join('$DATA_DIR', 'cybersecurity_sharegpt.jsonl'), orient='records', lines=True, force_ascii=False)

	print('下载 cnvd_vulnerability...')
	ds = load_dataset('lxcxjxhx/infosec-dataset-training', 'cnvd_vulnerability')
	ds['train'].to_json(os.path.join('$DATA_DIR', 'cnvd_vulnerability.jsonl'), orient='records', lines=True, force_ascii=False)

	print('下载 merged_cybersec...')
	ds = load_dataset('lxcxjxhx/infosec-dataset-training', 'merged_cybersec')
	ds['train'].to_json(os.path.join('$DATA_DIR', 'merged_cybersec.jsonl'), orient='records', lines=True, force_ascii=False)

	print('数据集下载完成!')
	"

	# 数据清洗
	echo "[2/4] 数据清洗..."
	python scripts/clean_data.py

	# 验证数据集
	echo "[3/4] 验证数据集..."
	python -c "
	import json
	import os

	data_dir = '$DATA_DIR'
	files = ['cybersecurity_hq.jsonl', 'cybersecurity_sharegpt.jsonl', 'cnvd_vulnerability.jsonl', 'merged_cybersec.jsonl']

	for f in files:
	path = os.path.join(data_dir, f)
	if os.path.exists(path):
	with open(path, 'r', encoding='utf-8') as file:
	count = sum(1 for _ in file)
	print(f'{f}: {count} 条记录')
	else:
	print(f'{f}: 文件不存在!')
	"

	# 复制 dataset_info.json
	echo "[4/4] 配置数据集信息..."
	cp datasets/dataset_info.json "$DATA_DIR/dataset_info.json" 2>/dev/null \|\| echo "dataset_info.json 已存在"

	echo "============================================"
	echo " 数据集准备完成!"
	echo "============================================"