OmniDocBench
Read the Portuguese translation →
Mentioned in
Section titled “Mentioned in”- This Local 1.2B OCR Model Beats GPT-5.2 (and Runs on 8GB GPU) — TeleOCR
- From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam
Related
Section titled “Related”vLLM, Transformers, Gradio, China Telecom, llama.cpp, Transformer