A Comprehensive Toolkit for High-Quality PDF Content Extraction

TF-ID: Table/Figure IDentifier for academic papers

A simple, easy-to-hack GraphRAG implementation

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

A simple unified framework for evaluating LLMs

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"

Train transformer language models with reinforcement learning.

Module, Model, and Tensor Serialization/Deserialization

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

AI Observability & Evaluation

SimPO: Simple Preference Optimization with a Reference-Free Reward

Recipes to train reward model for RLHF.

RAGChecker: A Fine-grained Framework For Diagnosing RAG

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

A Large-Scale Few-Shot Relation Extraction Dataset

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search…

Retrieval-Augmented Generation-based Relation Extraction

Context-Aware Representations for Knowledge Base Relation Extraction

Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"

Blazingly fast LLM inference.