A WebGL viewer for UMAP or TSNE-clustered images

Code to easily try 30 (and growing) different image matching methods

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

A curated list of awesome LLM for Autonomous Driving resources (continually updated)

Template for Python Projects

A minimal implementation of vllm.

A PyTorch implementation of text-to-3D models, e.g., DreamFusion and Magic3D, based on NerfAcc

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Llama2 transformer walkthrough with code examples

(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)

Function to calculate mAP for set of detected boxes and annotated boxes.

Most popular metrics used to evaluate object detection algorithms.

HIP: C++ Heterogeneous-Compute Interface for Portability

LLM101n: Let's build a Storyteller

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

TensorRT integration of YOLOXP with detections and segmentations

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️

Stack trace visualizer

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

The Linux perf GUI for performance analysis.

PS3 emulator/debugger

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

A generative speech model for daily dialogue.

A personal wearable AI that runs locally