AGENT SKILLS · ミッション装備 / orchestra-research

orchestra-research · Agent Skills

出典を確認した実質的な文書を持つ Skill が 94 件あります。カードを開くと原文、パッケージ内容、導入方法を確認できます。

orchestra-research
コミュニティ

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

nanogpt

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

nemo-evaluator-sdk

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

nnsight-remote-interpretability

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

optimizing-attention-flash

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

outlines

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

phoenix-observability

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

pinecone

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

presenting-conference-talks

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

prompt-guard

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

pytorch-fsdp2

Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

pytorch-lightning

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

pyvene-interventions

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

quantizing-models-bitsandbytes

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

1時間の導入数
2
GitHub Stars
1.3万
更新日
6月16日
orchestra-research
コミュニティ

ray-data

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

rwkv-architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日
orchestra-research
コミュニティ

segment-anything-model

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

1時間の導入数
2
GitHub Stars
1.4万
更新日
10月11日