huridocs / pdf-reading-order
☆13Updated 11 months ago
Alternatives and similar repositories for pdf-reading-order:
Users that are interested in pdf-reading-order are comparing it to the libraries listed below
- Small python package to measure OCR quality and other related metrics.☆21Updated last year
- Large-scale query-focused multi-document Summarization dataset☆10Updated 3 years ago
- ☆18Updated 3 months ago
- Using short models to classify long texts☆21Updated 2 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆29Updated 2 years ago
- This repository is part of an NLP course for humanities and cultural studies. This course uses historical newspapers as a source and appl…☆16Updated last month
- [COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training☆16Updated 6 months ago
- ☆14Updated 6 months ago
- NLG Best Practices for Data-Efficient Modeling How to Train Production-Ready Models with Little Data☆10Updated 3 years ago
- ☆14Updated 6 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆19Updated 2 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆48Updated last year
- Streamlit Named Entity Recognition (NER) annotation custom component☆38Updated 2 years ago
- Efficient few-shot learning with cross-encoders.☆51Updated last year
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆19Updated 3 weeks ago
- ☆16Updated 3 years ago
- An open-source NLP library: fast text cleaning and preprocessing☆23Updated 3 years ago
- Index of URLs to pdf files all over the internet and scripts☆23Updated last year
- ☆23Updated 2 months ago
- FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction☆24Updated 2 years ago
- ☆25Updated 6 years ago
- Experiments for XLM-V Transformers Integeration☆13Updated 2 years ago
- ☆12Updated last year
- ☆11Updated 4 months ago
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- KITE (Knowledge-Intensive Task Evaluation) is an end-to-end benchmark for RAG pipelines☆14Updated 8 months ago
- ☆28Updated last week
- Library for fast text representation and classification.☆28Updated last year
- ☆28Updated last year
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆34Updated last year