AI Agent Skills

Silero Models: pre-trained text-to-speech models made embarrassingly simple

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit con…

Run multimodal agents that operate desktop interfaces

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inferen…

A framework for efficient model inference with omni-modality models

A unified inference and post-training framework for accelerated video generation.

Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.

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

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

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Chronos: Pretrained Models for Time Series Forecasting

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Advancing Open-source World Models

A general fine-tuning kit geared toward image/video/audio diffusion models.

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all throug…