orchestra-re search · 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。
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.5万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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
- 1時間の導入数
- 2
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 2
- GitHub Stars
- 1.3万
- 更新日
- 6月16日
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.
- 1時間の導入数
- 1
- GitHub Stars
- 1.5万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 1
- GitHub Stars
- 1.5万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 1
- GitHub Stars
- 1.4万
- 更新日
- 10月11日
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.
- 1時間の導入数
- 1
- GitHub Stars
- 1.5万
- 更新日
- 10月11日
