AI Agent Skills

The 𝗣𝗼𝘄𝗲𝗿𝗳𝘂𝗹 Conversational AI JavaScript Library 💬 — UI for any LLM, supporting LangChain / HuggingFace / Vercel AI, and more 🧡 React, Next.js, and plain Java…

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

Cybertron: the home planet of the Transformers in Go

A blazing fast inference solution for text embeddings models

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (ad…

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl /…

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

论文抓取（3 步流水线的第 1 步）。抓取 arXiv + HuggingFace 最新论文，打分筛选，富化信息， 输出到 /tmp/daily_papers_enriched.json 供后续 skill 使用。 触发词："论文抓取"、"跑一下论文抓取" 支持多天模式："过去3天论文推荐"、"过去一周论文推荐"、"过去一周的论文"、"…

Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation, audio tran…

[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

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