github.com/Orchestra-Research/AI-Research-SKILLs14.2k

AI-Research-SKILLs

Comprehensive open-source library of AI research and engineering skills for any AI model.

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs

48 skills

Academic Figure Plotting

Generates publication-quality architecture diagrams and data charts for ML papers.

Orchestra-Research/AI-Research-SKILLs14.2k

Ara Compiler

Compiles any research input, PDF papers, GitHub repositories, experiment logs, code...

Orchestra-Research/AI-Research-SKILLs14.2k

Ara Research Manager

Records research provenance as a post-task epilogue, scanning conversation history at...

Orchestra-Research/AI-Research-SKILLs14.2k

Ara Rigor Reviewer

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts...

Orchestra-Research/AI-Research-SKILLs14.2k

Audiocraft Audio Generation

PyTorch library for audio generation including text-to-music (MusicGen) and...

Orchestra-Research/AI-Research-SKILLs14.2k

Autoresearch

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture.

Orchestra-Research/AI-Research-SKILLs14.2k

Awq Quantization

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and...

Orchestra-Research/AI-Research-SKILLs14.2k

Axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models...

Orchestra-Research/AI-Research-SKILLs14.2k

Blip 2 Vision Language

Vision-language pre-training framework bridging frozen image encoders and LLMs.

Orchestra-Research/AI-Research-SKILLs14.2k

Brainstorming Research Ideas

Guides researchers through structured ideation frameworks to discover high-impact...

Orchestra-Research/AI-Research-SKILLs14.2k

Chroma

Open-source embedding database for AI applications.

Orchestra-Research/AI-Research-SKILLs14.2k

Clip

OpenAI's model connecting vision and language.

Orchestra-Research/AI-Research-SKILLs14.2k

Constitutional AI

Anthropic's method for training harmless AI through self-improvement.

Orchestra-Research/AI-Research-SKILLs14.2k

Creative Thinking For Research

Applies cognitive science frameworks for creative thinking to CS and AI research ideation.

Orchestra-Research/AI-Research-SKILLs14.2k

Distributed LLM Pretraining Torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D...

Orchestra-Research/AI-Research-SKILLs14.2k

Dspy

Build complex AI systems with declarative programming, optimize prompts automatically...

Orchestra-Research/AI-Research-SKILLs14.2k

Evaluating Code Models

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks...

Orchestra-Research/AI-Research-SKILLs14.2k

Evaluating Cosmos Policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments.

Orchestra-Research/AI-Research-SKILLs14.2k

Evaluating Llms Harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA...

Orchestra-Research/AI-Research-SKILLs14.2k

Evolving AI Agents

Provides guidance for automatically evolving and optimizing AI agents across any domain...

Orchestra-Research/AI-Research-SKILLs14.2k

Experiment Tracking Swanlab

Provides guidance for experiment tracking with SwanLab.

Orchestra-Research/AI-Research-SKILLs14.2k

Faiss

Facebook's library for efficient similarity search and clustering of dense vectors.

Orchestra-Research/AI-Research-SKILLs14.2k

Fine Tuning Openvla Oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action...

Orchestra-Research/AI-Research-SKILLs14.2k

Fine Tuning Serving Openpi

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using...

Orchestra-Research/AI-Research-SKILLs14.2k

Fine Tuning With Trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO...

Orchestra-Research/AI-Research-SKILLs14.2k

Gguf Quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

Orchestra-Research/AI-Research-SKILLs14.2k

Gptq

Post-training 4-bit quantization for LLMs with minimal accuracy loss.

Orchestra-Research/AI-Research-SKILLs14.2k

Grpo Rl Training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model...

Orchestra-Research/AI-Research-SKILLs14.2k

Guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation...

Orchestra-Research/AI-Research-SKILLs14.2k

Hqq Quantization

Half-Quadratic Quantization for LLMs without calibration data.

Orchestra-Research/AI-Research-SKILLs14.2k

Huggingface Tokenizers

Fast tokenizers optimized for research and production.

Orchestra-Research/AI-Research-SKILLs14.2k

Implementing Llms Litgpt

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained...

Orchestra-Research/AI-Research-SKILLs14.2k

Instructor

Extract structured data from LLM responses with Pydantic validation, retry failed...

Orchestra-Research/AI-Research-SKILLs14.2k

Knowledge Distillation

Compress large language models using knowledge distillation from teacher to student...

Orchestra-Research/AI-Research-SKILLs14.2k

Langsmith Observability

LLM observability platform for tracing, evaluation, and monitoring.

Orchestra-Research/AI-Research-SKILLs14.2k

Llama Cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Orchestra-Research/AI-Research-SKILLs14.2k

Llama Factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models...

Orchestra-Research/AI-Research-SKILLs14.2k

Llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering.

Orchestra-Research/AI-Research-SKILLs14.2k

Llava

Large Language and Vision Assistant.

Orchestra-Research/AI-Research-SKILLs14.2k

Long Context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position...

Orchestra-Research/AI-Research-SKILLs14.2k

Mamba Architecture

State-space model with O(n) complexity vs Transformers' O(n²).

Orchestra-Research/AI-Research-SKILLs14.2k

Miles Rl Training

Provides guidance for enterprise-grade RL training using miles, a production-ready fork...

Orchestra-Research/AI-Research-SKILLs14.2k

Ml Paper Writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM.

Orchestra-Research/AI-Research-SKILLs14.2k

Ml Training Recipes

Battle-tested PyTorch training recipes for all domains, LLMs, vision, diffusion...

Orchestra-Research/AI-Research-SKILLs14.2k

Mlflow

Track ML experiments, manage model registry with versioning, deploy models to...

Orchestra-Research/AI-Research-SKILLs14.2k

Modal Serverless Gpu

Serverless GPU cloud platform for running ML workloads.

Orchestra-Research/AI-Research-SKILLs14.2k

Model Merging

Merge multiple fine-tuned models using mergekit to combine capabilities without...

Orchestra-Research/AI-Research-SKILLs14.2k

Model Pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and...

Orchestra-Research/AI-Research-SKILLs14.2k