ElephantGit
Follow
Starred repositories
Persist and reuse KV Cache to speedup your LLM.
Zero and Few shot named entity & relationships recognition
dylanhogg / GLiNER2
Forked from fastino-ai/GLiNER2Unified Schema-Based Information Extraction
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024
这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
MAGI-1: Autoregressive Video Generation at Scale
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
PyTorch code and models for the DINOv2 self-supervised learning method.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Simple, online, and realtime tracking of multiple objects in a video sequence.
A latent text-to-image diffusion model
Generative Models by Stability AI
Refine high-quality datasets and visual AI models
Official repo for consistency models.
LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
[ICLR2022] official implementation of UniFormer
[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
😎 Awesome lists about all kinds of interesting topics
A curated list of awesome model based RL resources (continually updated)
Decision Intelligence platform for Traffic Crossing Signal Control
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
This is a collection of our NAS and Vision Transformer work.
