orchestra-re search · Agent Skills
출처를 확인한 실질적인 문서가 있는 Skill 94개입니다. 카드를 열어 원문, 패키지 구성과 설치 방법을 확인하세요.
fine-tuning-serving-openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
fine-tuning-with-trl
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
grpo-rl-training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
- 1시간 설치 수
- 2
- GitHub Stars
- 1.3만
- 업데이트
- 6월 16일
hqq-quantization
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
huggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.3만
- 업데이트
- 6월 16일
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.3만
- 업데이트
- 6월 16일
llama-cpp
Runs 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 4-10× speedup vs PyTorch on CPU.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
llamaguard
Meta'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.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.3만
- 업데이트
- 6월 16일
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.3만
- 업데이트
- 6월 16일
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — 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. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
- 1시간 설치 수
- 2
- GitHub Stars
- 1.4만
- 업데이트
- 10월 11일
