[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
- pytorch
- video-retrieval
- video-question-answering
- vqa
142,273 visible repositories in the index
1,729–1,752 of 2,392 · Most stars
[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
An open-source, feature rich & extensible url-shortener + analytics written in Python :cookie:
Semantic Text Similarity Dataset Hub
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Pytorch实现的流式与非流式的自动语音识别框架,同时兼容在线和离线识别,目前支持Conformer、Squeezeformer、DeepSpeech2模型,支持多种数据增强方法。
Fat-Cat: A document-centric context management Agent. Making context as simple as reading chat history.
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
Vim for Sublime Text.
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
CAD MCP Server
Latent Couple extension (two shot diffusion port)
Display, extract, and manipulate PSP firmware inside UEFI images
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
StoryMaker: Towards consistent characters in text-to-image generation
Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
Sublime Text plugin for creating new Gists from selected text
飞牛音乐扩展在线音乐
A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use
Home Assistant integration for Sungrow inverters: SH*RT series (SH10RT), SHx.RS series (SH3.RS), SH*K series (SH4K6), SxT-series (S20T)
NucliaDB, The AI Search database for RAG
High-performance Text-to-Speech server with OpenAI-compatible API, 8 voices, emotion tags, and modern web UI. Optimized for RTX GPUs.
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.