10,232 skills found ¡ Page 69 of 342
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 / moe-trainingTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace
Orchestra-Research / speculative-decodingAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques
Orchestra-Research / ml-paper-writingWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM
Orchestra-Research / ara-compilerCompiles any research input â PDF papers, GitHub repositories, experiment logs, code directories, or raw notes â into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence
Orchestra-Research / ara-rigor-reviewerPerforms ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong AâĻ
Orchestra-Research / distributed-llm-pretraining-torchtitanProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP)
Orchestra-Research / sentencepieceLanguage-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
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 / slime-rl-trainingProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework
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 / training-llms-megatronTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies
Orchestra-Research / skypilot-multi-cloud-orchestrationMulti-cloud orchestration for ML workloads with automatic cost optimization
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
Orchestra-Research / gguf-quantizationGGUF format and llama.cpp quantization for efficient CPU/GPU inference
Orchestra-Research / hqq-quantizationHalf-Quadratic Quantization for LLMs without calibration data
Orchestra-Research / llama-cppRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10Ã speedup vs PyTorch on CPU.
Orchestra-Research / tensorrt-llmOptimizes 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.
Orchestra-Research / serving-llms-vllmServes LLMs with high throughput using vLLM's PagedAttention and continuous batching
Orchestra-Research / autogpt-agentsAutonomous AI agent platform for building and deploying continuous agents
Orchestra-Research / faissFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata.
Orchestra-Research / langsmith-observabilityLLM observability platform for tracing, evaluation, and monitoring
Orchestra-Research / phoenix-observabilityOpen-source AI observability platform for LLM tracing, evaluation, and monitoring
