OpenSparX-7b-cabin-sft-v2-gptq-int4

简介 | Overview

这是一个基于 Qwen2.5-VL-7B-Instruct 的多模态座舱助手模型，使用 GPTQ INT4 量化，面向资源受限但仍需要较强视觉理解和指令跟随能力的车机或边缘部署场景。

This is a multimodal in-cabin assistant model based on Qwen2.5-VL-7B-Instruct and quantized with GPTQ INT4. It targets edge or in-vehicle deployments where memory is limited but strong visual understanding is still required.

适用场景 | Use Cases

• 座舱情绪识别与安抚建议。

• 驾驶分心行为识别与安全提醒。

• 儿童安全带佩戴检测与提醒。

• 输出自然语言回复和结构化控制标签，便于接入车机控制链路。

• Emotion recognition and comfort suggestions in the cabin.

• Driver distraction detection and safety reminders.

• Child seat-belt wearing detection and reminders.

• Natural-language responses plus structured action tags for downstream vehicle control integration.

推荐输入格式 | Recommended Input Format

推荐使用 Qwen2.5-VL 的多模态消息格式，图像和文本通过 content 数组一起传入。

Use the native Qwen2.5-VL multimodal message format, where image and text are passed together in the content array.

{
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "image"},
        {"type": "text", "text": "请根据图像描述驾驶员状态并给出功能建议。"}
      ]
    }
  ]
}

Python 推理示例 | Python Inference Example

该模型是视觉语言模型，推理时应使用 AutoProcessor 和 Qwen2_5_VLForConditionalGeneration。

This model is a vision-language model, so inference should use AutoProcessor and Qwen2_5_VLForConditionalGeneration.

from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration

repo_id = "qualcomm-ai-hub-community/OpenSparX-7b-cabin-sft-v2-gptq-int4"
processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

image = Image.open("/path/to/your/image.jpg").convert("RGB")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "Describe the driver state and suggest actions."},
        ],
    }
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")
inputs = inputs.to(model.device)

generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids = [
    output_ids[len(input_ids):]
    for input_ids, output_ids in zip(inputs.input_ids, generated_ids)
]
print(processor.batch_decode(generated_ids, skip_special_tokens=False)[0])

文件说明 | File Overview

• model-00001-of-00002.safetensors、model-00002-of-00002.safetensors、model.safetensors.index.json：模型权重与索引。

• config.json：模型结构配置，基座为 Qwen2.5-VL-7B-Instruct。

• quantize_config.json：GPTQ INT4 量化配置。

• preprocessor_config.json：视觉预处理配置。

• chat_template.json：对话模板。

• model-00001-of-00002.safetensors, model-00002-of-00002.safetensors, and model.safetensors.index.json: model shards and index.

• config.json: model architecture config based on Qwen2.5-VL-7B-Instruct.

• quantize_config.json: GPTQ INT4 quantization settings.

• preprocessor_config.json: visual preprocessing config.

• chat_template.json: chat template used for prompt construction.

资源需求 | Requirements

建议使用支持 GPTQ 的推理环境，显存建议 12 GB 以上，实际需求受输入分辨率和生成长度影响。

Use a GPTQ-capable inference stack. A GPU with at least 12 GB VRAM is recommended, although actual usage depends on image resolution and generation length.

注意事项 | Notes

模型仅用于研究与演示。若要部署到真实驾驶环境，请补充安全评估、异常回退和权限控制。

This model is intended for research and demo use only. For real driving deployment, add safety validation, fallback handling, and permission control.