Baidu Releases Unlimited-OCR: Open-Source Model for One-Shot Long-Horizon Document Parsing
By
ingve
Summary
Baidu has released Unlimited-OCR, an open-source OCR model designed for one-shot long-horizon parsing. The model can process entire documents or long-form content in a single pass, eliminating the need for chunking or multiple processing steps. It supports inference via Huggingface Transformers on NVIDIA GPUs and is available on GitHub under the baidu organization. The repository includes code examples for loading the model with PyTorch and transformers, using bfloat16 precision and safetensors for efficient inference.
Source
Hacker NewsBaidu Releases Unlimited-OCR: Open-Source Model for One-Shot Long-Horizon Document Parsinggithub.comKey quotes
· 2 pulledWelcome the Era of One-shot Long-horizon Parsing.
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
You might also wanna read
Unlimited OCR - a Hugging Face Space by baidu
Unlimited OCR - a Hugging Face Space by baidu
RTP-LLM: Alibaba's High-Performance Inference Engine for Large Language Model Deployment
This paper presents RTP-LLM, a high-performance inference engine developed by Alibaba for industrial-scale deployment of Large Language Mode
arxiv.org·25d ago
Nolain OCR: Convert Documents to Spreadsheets with Consistent Data Extraction
Nolain OCR is a document processing service that converts multiple documents (forms, receipts, invoices) into structured spreadsheet data wi
Product Hunt·4mo ago
Building a Minimal RAG System from Scratch: PDF to Highlighted Answers in ~100 Lines of Python
A hands-on tutorial that builds the smallest functional RAG (Retrieval-Augmented Generation) system from scratch using about 100 lines of Py
towardsdatascience.com·24d ago
Krea 2 Raw: A Text-to-Image Model Checkpoint for Fine-Tuning on Hugging Face
This is a Hugging Face repository page for the Krea 2 Raw text-to-image model checkpoint. The model is not intended for direct inference but
A Practical Guide to Scaling Language Models: From Single Accelerators to Thousands
This article/book excerpt demystifies the science of scaling language models, explaining how TPUs and GPUs work, how they communicate, how L
jax-ml.github.io·2d agoComments
Sign in to join the conversation.
No comments yet. Be the first.