orchestra-re search · Agent Skills
94 Skills avec une documentation substantielle et des sources vérifiées. Ouvrez une fiche pour lire les instructions originales et vérifier le paquet et son installation.
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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).
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 12,6 k
- Mis à jour
- 16 juin
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
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.
- Installations / 1h
- 2
- GitHub Stars
- 14,1 k
- Mis à jour
- 11 oct.
