lvyufeng

🌟 Github | 📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link | The official version of DeepSeek-OCR has limited the transformers version to 4.46.3 and has not been adapted to the latest version. Therefore, this community edition has modified the modeling.py module to facilitate user convenience without requiring a transformers downgrade. Additionally, this version has been adapted for MindSpore+MindNLP compatibility, and users are welcome to utilize it on Ascend hardware. Feel free to opt for various attention implementations such as Flash Attention or SDPA to leverage the latest optimizations in transformers for a performance boost. MindSpore Usage Inference using Huggingface transformers on Ascend NPUs. Requirements tested on MindSpore2.7+ CANN8.2： Pytorch Usage Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8： We would like to thank Vary, GOT-OCR2.0, MinerU, PaddleOCR, OneChart, Slow Perception for their valuable models and ideas. We also appreciate the benchmarks: Fox, OminiDocBench.