Stars
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
An autoregressive character-level language model for making more things
Truthfulqa_indic, Available in Hindi, Punjabi, Kannada, Tamil and Telugu
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024
showing various ways to serve Keras based stable diffusion
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m…
Unsupervised text tokenizer for Neural Network-based text generation.
Instruction Tuning with GPT-4
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Labelled image dataset for door and handle detection.
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Inpaint anything using Segment Anything and inpainting models.
MPNet: Masked and Permuted Pre-training for Language Understanding https://arxiv.org/pdf 9993 /2004.09297.pdf
Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHX…
⚡ Langchain apps in production using Jina & FastAPI
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
Examples for using ONNX Runtime for model training.
Visually simulate Git operations in your own repos with a single terminal command.
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
The official implementation of the paper "Human Motion Diffusion as a Generative Prior"
Cross-platform, customizable ML solutions for live and streaming media.
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform…
LAVIS - A One-stop Library for Language-Vision Intelligence