audiocraft

Comprehensive guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, a...

github

creative-thinking-for-research

Eight empirically grounded frameworks from cognitive science, applied to computer science and AI research. Unlike ad-hoc...

github

openpi

End-to-end workflows for fine-tuning and serving Physical Intelligence's OpenPI models (pi0, pi0-fast, pi0.5) on robot m...

github

torchforge

torchforge is Meta's PyTorch-native RL library that separates infrastructure concerns from algorithm concerns. It enable...

github

chroma

The AI-native database for building LLM applications with memory. Use Chroma when: Building RAG (retrieval-augmented gen...

github

llama-factory

Comprehensive assistance with llama-factory development, generated from official documentation. This skill should be tri...

github

constitutional-ai

Constitutional AI (CAI) trains models to be harmless through self-critique and AI feedback, without requiring human labe...

github

lm-evaluation-harness

lm-evaluation-harness evaluates LLMs across 60+ academic benchmarks using standardized prompts and metrics. Installation...

github

hqq

Fast, calibration-free weight quantization supporting 8/4/3/2/1-bit precision with multiple optimized backends. Use HQQ ...

github

long-context

Use Long Context techniques when you need to: Process long documents (32k, 64k, 128k+ tokens) with transformer models Ex...

github

huggingface-tokenizers

Fast, production-ready tokenizers with Rust performance and Python ease-of-use. Use HuggingFace Tokenizers when: Need ex...

github

moe-training

Use MoE Training when you need to: Train larger models with limited compute (5× cost reduction vs dense models) Scale mo...

github

nemo-guardrails

NeMo Guardrails adds programmable safety rails to LLM applications at runtime. Installation: pip install nemoguardrails ...

github

a-evolve

A-Evolve is universal infrastructure for evolving any AI agent across any domain using any evolution algorithm with zero...

github

nnsight

nnsight (/ɛn.saɪt/) enables researchers to interpret and manipulate the internals of any PyTorch model, with the unique ...

github

llamaguard

LlamaGuard is a 7-8B parameter model specialized for content safety classification. Installation: pip install transforme...

github

qdrant

High-performance vector database written in Rust for production RAG and semantic search. Use Qdrant when: Building produ...

github

segment-anything

Comprehensive guide to using Meta AI's Segment Anything Model for zero-shot image segmentation. Use SAM when: Need to se...

github

axolotl

Comprehensive assistance with axolotl development, generated from official documentation. This skill should be triggered...

github

cosmos-policy

Evaluation workflows for NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments from the public cosmos-poli...

github

outlines

Use Outlines when you need to: Guarantee valid JSON/XML/code structure during generation Use Pydantic models for type-sa...

github

mlflow

Use MLflow when you need to: Track ML experiments with parameters, metrics, and artifacts Manage model registry with ver...

github

accelerate

Accelerate simplifies distributed training to 4 lines of code. Installation: pip install accelerate Convert PyTorch scri...

github

unsloth

Comprehensive assistance with unsloth development, generated from official documentation. This skill should be triggered...

github