machbase-neo = time series database + mqtt + http + data visualization

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

Multimodal saree search app built using Amazon Titan Multimodal Embeddings model

[TPAMI 2024 & CVPR 2023] PyTorch code for DGM4: Detecting and Grounding Multi-Modal Media Manipulation and beyond

A comprehensive benchmark of deepfake detection

🎓 Update Talking-Face Research Papers Daily, Now Integrated with LLM Analysis.

A compilation of the best multi-agent papers

PyTorch code and models for V-JEPA self-supervised learning from video.

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Tools for building GPU clusters

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Official repository for ORPO

20회 ADP를 준비한 python 파일들을 모아놓은 repository

📗 '만개의 레시피’ 데이터를 활용한 추천 시스템 - 레시피와 리뷰를 중심으로

This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc

ChatGPT, GenerativeAI and LLMs Timeline

Efficient fine-tuning for ko-llm models

Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmind

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Code for "Unsupervised Pretraining for Fact Verification by Language Model Distillation" (ICLR 2024)

Korean Multi-task Instruction Tuning

Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, Cont…