Stars
A little Python script to generate Cohen's Kappa and Weighted Kappa measures for inter-rater reliability
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
An open-source RAG-based tool for chatting with your documents.
Best practices for distilling large language models.
Distribute and run LLMs with a single file.
A Streamlit component for annotating text by text selecting.
Library for fast text representation and classification.
Experimental new Python bindings for the VowpalWabbit library
🦜🔗 Build context-aware reasoning applications
DocILE: Document Information Localization and Extraction Benchmark
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
Manipulate JSON-like data with NumPy-like idioms.
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
A system for quickly generating training data with weak supervision
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Tensorflow Implementation of Convolutional Neural Network for Relation Extraction (COLING 2014, NAACL 2015)
🦉 Modern high-performance serialization utilities for Python (JSON, MessagePack, Pickle)
PromptORE – A Novel Approach Towards Fully Unsupervised Relation Extraction
Data programming by demonstration for information extraction and span annotation
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
A library of sklearn compatible categorical variable encoders
Pre-trained word embeddings using the text of published clinical case reports.
brat rapid annotation tool (brat) - for all your textual annotation needs
Conversion from brat-flavored standoff to CoNLL format
This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs