lsl1229840757
Follow
Lists (4)
Stars
搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
A library for human kinematic motion and numerical optimization solvers to apply human motion
LAVIS - A One-stop Library for Language-Vision Intelligence
Examples and guides for using the OpenAI API
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
VMamba: Visual State Space Models，code is based on mamba
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Build high-performance AI models with modular building blocks
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
A General-purpose Person Re-identification Task with Instructions
Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory wh…
[Arxiv-2024] MotionLLM: Understanding Human Behaviors from Human Motions and Videos
LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
A framework for prompt tuning using Intent-based Prompt Calibration
Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision [AAAI2023 Oral]]
The official repository for ICLR2024 paper "FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition"
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)