Public KG record
LoRA
Recorded overview
Low-Rank Adaptation used to train the model to handle designer and coder roles w
Extract text from images, scans, or PDFs while preserving layout, tables, and document structure.
Recorded details
- Capabilities: 支持本地微调
- Capabilities: 支持LoRA微调
- Capabilities: 提供文本生成图像和图像编辑两类 DreamBooth LoRA 训练脚本
- Capabilities: trained on top of the DharmaOCR-LITE v1.1 checkpoint using 43,384 training examples covering both request modes
- Supported types: 图像生成与图像角度变换
Evidence coverage
The KG currently records 8 known information dimensions and has 11 undocumented dimensions, linked to 14 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- ML-intern — uses
- Samaya Sterling — uses
- Microsoft — develops
- DPO — uses
- GSPO — uses