Stars
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Machine Learning Engineering Open Book
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Wiki.js | A modern and powerful wiki app built on Node.js
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Everything I know about machine learning and camera traps.
An extremely fast Python linter and code formatter, written in Rust.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Python packaging and dependency management made easy
Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Distributed Task Queue (development branch)
LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations.
A production ready example Flask app that's using Docker and Docker Compose.
Simplify camera trap image analysis with ML species recognition models based around the MegaDetector model
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
BirdNET analyzer for scientific audio data processing.