冻结 Gemma 4 E4B 基座 + 决策 LoRA，每题一次前向读出全部选项概率。 支持 Choice（2–20项）、Score（2–10级）、yes/no，覆盖文本、图像、截图、音频与视频。 API直接返回答案概率、置信度和结构化判断。 MMAU音频路由基座方案采用65.9%的实测结果；默认部署脚本采用全模态adapter。 真实模型工作台通过三类判断、图像/截图/音频/视频、cURL重放及错误恢复验证。 GGUF三档在20个公开文本案例上均与参考选答20/20一致，截图、音频和视频运行探针全部成功。 环境：Linux x8664、Python3.11、兼容CUDA13的NVIDIA驱动；FP32配方在H20 96GB实测显存约39GB。 终端B启动API和工作台： 打开本地工作台，或调用API： 每题返回probabilities、confidence及相应的choice、score或noul。 Score为从0开始的期望等级；Noul为yes的概率。部署脚本使用原始答案概率（calibration: unfitted）。 媒体通过服务端受信文件路径和SHA256引用： type也支持audio/video；视频用videoframes选择8或16帧。 GGUF截图采用RGB、长边≤1344；完整命令见gateway/GGUF.md。
Publisher
Chinzhu
Chinzhu
Models in Library1
Datasets in Library0
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image and text to text.
Reported licenses: cc-by-nc-sa-4.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.