HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

Code for the MedRAG toolkit

Official repository of the MIRAGE benchmark

paper list, dataset, and tools for radiology report generation

Benchmarking library for RAG

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…

많이 다뤄지는 기술 면접 질문 리스트 (기본 CS 부터 프론트엔드, 백엔드, 데이터, AI/ML 까지)

Codebase for Quilt-LLaVA

Large Language-and-Vision Assistant for BioMedicine, built towards multimodal GPT-4 level capabilities.

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Efficient Triton Kernels for LLM Training

llama3 implementation one matrix multiplication at a time

The technical interview knowledge that a junior backend developer should possess.

RandStainNA: Simple and efficient augmentations for histology [MICCAI 2022]

Pretrained model for self supervised histopathology

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

PyTorch native post-training library

Train a model to predict gene expression from histology slides.

Code for ALBEF: a new vision-language pre-training method

Official implementation of project Honeybee (CVPR 2024)

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

Code

Official Codes for "Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes"

Machine Learning Engineering Open Book

Official inference library for Mistral models

A framework for few-shot evaluation of language models.