Repository Issue Activity (beta)

#69 Your project is on StackMap — a curated map of the AI stack

#97 [Feature Request] Add Agent skill/tool integration interface for OCR capability

#82 Output texts keeps on repeating infinitely [Tried with llama.cpp server running on ubuntu 22.04]

#18 Apple Silicon (MPS): empty output — masked_scatter with a broadcast mask scatters incorrectly on Metal

#95 ArabicOCR

#94 Is the source code for the Hugging Face Spaces web demo available?

#93 模型推理部署

#90 Hebrew text: model outputs a hallucinated token while Latin text on the same image is read correctly — is Hebrew supported?

#89 Enhancement / Discussion: Benchmark and Support for Arabic Language Parsing via arafix

#88 dokOSR

#66 OmniDocBench v1.6 text EditDist: we measure 0.087 vs ~0.042 implied by the reported Overall — CDM/TEDS at parity; requesting eval methodology

#87 Herramientas

#3 Language Support

#84 Patent's ST.25 listings become tables and digit-changing generation loops in vLLM

#83 Review the Engineer's response

#81 Non-CUDA inference: CPU works after removing hardcoded .cuda(); MPS (Apple Silicon) crashes mid-generation

#12 UnlimitedOCRForCausalLM not supported by SGLang (ValueError)

#74 Verify evals on Papers with Code

#79 Rotated text parsing drops multiple text lines and generates a spurious line during OCR

#78 Improve error handling for unsupported input formats in `model.infer()`

#76 Total number of attention heads (10) must be divisible by tensor parallel size (4)

#45 手写的文字 效果不是特别好

#25 Language support list

#16 针对扫描 PDF 识别效果不佳问题

#6 可视化模块是怎么做的