Robust Speech Recognition via Large-Scale Weak Supervision

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Inference code for Llama models

A programming framework for agentic AI

Ultralytics YOLO 🚀

A lightweight, powerful framework for multi-agent workflows

Inference code for CodeLlama models

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

An elegant PyTorch deep reinforcement learning library.

End-to-End Speech Processing Toolkit

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

🔎 📈 🐍 💰 Backtest trading strategies in Python.

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

A debugging and profiling tool that can trace and visualize python code execution

A Unified Toolkit for Deep Learning Based Document Image Analysis

Production First and Production Ready End-to-End Speech Recognition Toolkit

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

GLIDE: a diffusion-based text-conditional image synthesis model

Hummingbird compiles trained ML models into tensor computation for faster inference.

Converts profiling output to a dot graph.

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.

Open a terminal in colab, including the free tier.

Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.