930 skills found ¡ Page 6 of 31
Orchestra-Research / nemo-curatorGPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16Ã faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS.
Orchestra-Research / openrlhf-trainingHigh-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. 2Ã faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Orchestra-Research / fine-tuning-with-trlFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training
Orchestra-Research / constitutional-aiAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Orchestra-Research / llamaguardMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Orchestra-Research / nemo-guardrailsNVIDIA'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.
Orchestra-Research / ray-trainDistributed 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
Orchestra-Research / gptqPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Ã memory reduction with <2% perplexity degradation, or for faster inference (3-4Ã speedup) vs FP16.
Orchestra-Research / ml-training-recipesBattle-tested PyTorch training recipes for all domains â LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation
Orchestra-Research / chromaOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval.
Orchestra-Research / sentence-transformersFramework 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.
Orchestra-Research / clipOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning.
Orchestra-Research / whisperOpenAI'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.
Orchestra-Research / peft-fine-tuningParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods
Orchestra-Research / grpo-rl-trainingExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Orchestra-Research / qdrant-vector-searchHigh-performance vector similarity search engine for RAG and semantic search
Orchestra-Research / audiocraft-audio-generationPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen)
Orchestra-Research / blip-2-vision-languageVision-language pre-training framework bridging frozen image encoders and LLMs
Orchestra-Research / knowledge-distillationCompress large language models using knowledge distillation from teacher to student models
Orchestra-Research / long-contextExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques
Orchestra-Research / model-pruningReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT
Orchestra-Research / speculative-decodingAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques
Orchestra-Research / axolotlExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Orchestra-Research / miles-rl-trainingProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime
Orchestra-Research / simpo-trainingSimple 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.
Orchestra-Research / torchforge-rl-trainingProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms
Orchestra-Research / verl-rl-trainingProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL)
Orchestra-Research / awq-quantizationActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss
Orchestra-Research / quantizing-models-bitsandbytesQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss
Orchestra-Research / optimizing-attention-flashOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction
