AI Agent Skills

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

A framework for efficient model inference with omni-modality models

Deploy Your Frontend in a Single Command. Claude Code Skills supported.

Helios: Real Real-Time Long Video Generation Model

Docker Compose Continuous Deployment

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

Nelm is a Helm 4 alternative. It is a Kubernetes deployment tool that manages Helm Charts and deploys them to Kubernetes. The Nelm goal is to provide a modern alternativ…

End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Evaluate systematic strategy ideas through signal testing, statistical validation, decay, execution costs, and model-risk review.

A hardware-aware Codex skill for local MiniMax H3 video generation through ComfyUI

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and traini…

Port of OpenAI's Whisper model in C/C++