AGENT SKILLS · WYPOSAŻENIE MISJI / orchestra-research

orchestra-research · Agent Skills

Liczba Skills z obszerną dokumentacją o sprawdzonym źródle: 94. Otwórz kartę, aby przeczytać oryginalne instrukcje oraz sprawdzić zawartość pakietu i instalację.

orchestra-research
Społeczność

sentence-transformers

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

sentencepiece

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

sglang

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

skypilot-multi-cloud-orchestration

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

speculative-decoding

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

systems-paper-writing

Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

tensorrt-llm

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Instalacje / 1h
2
GitHub Stars
14,1 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Instalacje / 1h
2
GitHub Stars
12,6 tys.
Aktualizacja
16 cze
orchestra-research
Społeczność

evaluating-cosmos-policy

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Instalacje / 1h
1
GitHub Stars
14,7 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

fine-tuning-openvla-oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

Instalacje / 1h
1
GitHub Stars
14,7 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Instalacje / 1h
1
GitHub Stars
14,4 tys.
Aktualizacja
11 paź
orchestra-research
Społeczność

transformer-lens-interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Instalacje / 1h
1
GitHub Stars
14,7 tys.
Aktualizacja
11 paź