Publisher
orchestra-research
Public Claude skills and plugins from github.com/orchestra-research that Waxell has reviewed.
- 98 reviewed
- 25 no issues
- 70 to review
- 3 high risk
98 resultsorchestra-research
- autoresearchorchestra-researchOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations… Review findingsResearchAI & agents14k
- implementing-llms-litgptorchestra-researchImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need… No issuesResearchAI & agents14k
- mamba-architectureorchestra-researchState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM… Review findingsResearchDesign14k
- nanogptorchestra-researchEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By… Review findingsResearchAI & agents14k
- rwkv-architectureorchestra-researchRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN… Review findingsProductivityResearch14k
- distributed-llm-pretraining-torchtitanorchestra-researchProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama… Review findingsResearchAI & agents14k
- huggingface-tokenizersorchestra-researchFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece,… Review findingsResearchEngineering14k
- sentencepieceorchestra-researchLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight… Review findingsResearchDocuments14k
- axolotlorchestra-researchExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support High riskResearchAI & agents14k
- llama-factoryorchestra-researchExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support No issuesResearchEngineering14k
- peft-fine-tuningorchestra-researchParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU… Review findingsResearchDocuments14k
- unslothorchestra-researchExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization High riskResearchDocuments14k
- nnsight-remote-interpretabilityorchestra-researchProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when… Review findingsResearchAI & agents14k
- pyvene-interventionsorchestra-researchProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when… Review findingsResearchEngineering14k
- sparse-autoencoder-trainingorchestra-researchProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into… Review findingsResearchData & analytics14k
- transformer-lens-interpretabilityorchestra-researchProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via… Review findingsResearchAI & agents14k
- nemo-curatororchestra-researchGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality… No issuesData & analyticsImages, video & audio14k
- ray-dataorchestra-researchScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray… No issuesData & analyticsResearch14k
- grpo-rl-trainingorchestra-researchExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training No issuesResearchAI & agents14k
- miles-rl-trainingorchestra-researchProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with… No issuesResearchAI & agents14k
- openrlhf-trainingorchestra-researchHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray,… No issuesResearchAI & agents14k
- simpo-trainingorchestra-researchSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval… Review findingsResearchAI & agents14k
- slime-rl-trainingorchestra-researchProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing… No issuesResearchAI & agents14k
- torchforge-rl-trainingorchestra-researchProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean… No issuesResearchAI & agents14k
- fine-tuning-with-trlorchestra-researchFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward… Review findingsResearchAI & agents14k
- verl-rl-trainingorchestra-researchProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or… Review findingsResearchAI & agents14k
- constitutional-aiorchestra-researchAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with… No issuesResearchAI & agents14k
- llamaguardorchestra-researchMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons,… Review findingsResearchAI & agents14k
- nemo-guardrailsorchestra-researchNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking,… Review findingsResearchAI & agents14k
- prompt-guardorchestra-researchMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast… Review findingsResearchData & analytics14k
- huggingface-accelerateorchestra-researchSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP.… Review findingsResearchEngineering14k
- deepspeedorchestra-researchExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam,… Review findingsResearchSales & marketing14k
- training-llms-megatronorchestra-researchTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training… Review findingsResearchSales & marketing14k
- pytorch-fsdp2orchestra-researchAdds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed… No issuesResearchDocuments14k
- pytorch-lightningorchestra-researchHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal… Review findingsResearchEngineering14k
- ray-trainorchestra-researchDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in… Review findingsResearchAI & agents14k
- lambda-labs-gpu-cloudorchestra-researchReserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH… High riskResearchAI & agents14k
- modal-serverless-gpuorchestra-researchServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management,… Review findingsEngineeringResearch14k
- skypilot-multi-cloud-orchestrationorchestra-researchMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across… Review findingsResearchAI & agents14k
- awq-quantizationorchestra-researchActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models… Review findingsResearchAI & agents14k
- quantizing-models-bitsandbytesorchestra-researchQuantizes 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… Review findingsResearchAI & agents14k
- optimizing-attention-flashorchestra-researchOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers… Review findingsResearchDocuments14k
- gguf-quantizationorchestra-researchGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or… Review findingsResearchEngineering14k
- gptqorchestra-researchPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when… Review findingsResearchDocuments14k
- hqq-quantizationorchestra-researchHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing… Review findingsData & analyticsResearch14k
- ml-training-recipesorchestra-researchBattle-tested PyTorch training recipes for all domains, LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics,… No issuesEngineeringResearch14k
- evaluating-code-modelsorchestra-researchEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code… Review findingsEngineeringAI & agents14k
- evaluating-llms-harnessorchestra-researchEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality,… Review findingsResearchDocuments14k
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF