PyTorch native quantization and sparsity for training and inference

🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

Optimizing inference proxy for LLMs

An open source implementation of LFMs from Liquid AI: Liquid Foundation Models

o1-engineer is a command-line tool designed to assist developers in managing and interacting with their projects efficiently. Leveraging the power of OpenAI's API, this tool provides functionalitie…

Generalist Software Agents to Solve Soware Engineering Tasks

Official implementation of "OffsetBias: Leveraging Debiased Data for Tuning Evaluators"

다양한 방식의 한글 검색을 지원하는 스위프트 라이브러리입니다.

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Paper Reproduction Google SCoRE(Training Language Models to Self-Correct via Reinforcement Learning)

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)

GRadient-INformed MoE

Things you can do with the token embeddings of an LLM

High accuracy RAG for answering questions from scientific documents with citations

PASTA: Post-hoc Attention Steering for LLMs

Code for EMNLP 2024 paper "Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning"

Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

FastMLX is a high performance production ready API to host MLX models.

Brand new TTS solution

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Empowering RAG with a memory-based data interface for all-purpose applications!

Incremental Knowledge Graphs Constructor Using Large Language Models

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Models (LLMs).