Search
By Orchestra-Research
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | 49.Llamaindex Data framework for building LLM applications with RAG. An agent skill from Orchestra-Research/AI-Research-SKILLs. | Orchestra-Research/ | 13k | 2 repos | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 50 | 50.Long Context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. | Orchestra-Research/ | 13k | 2 repos | ~3.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 51 | Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. | Orchestra-Research/ | 13k | 2 repos | ~2.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 52 | Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. | Orchestra-Research/ | 13k | 2 repos | ~3.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 53 | 53.Moe Training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. | Orchestra-Research/ | 13k | 2 repos | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 54 | Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. | Orchestra-Research/ | 13k | 2 repos | ~3.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 55 | Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. | Orchestra-Research/ | 13k | 2 repos | ~3.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 56 | High-performance RLHF framework with Ray+vLLM acceleration. An agent skill from Orchestra-Research/AI-Research-SKILLs. | Orchestra-Research/ | 13k | 2 repos | ~2.1k | Automated safety check: Notes | MIT | 3 mo ago |
| 57 | Sets up Arize Phoenix to trace, evaluate and monitor LLM applications, with instrumentation for OpenAI, LangChain and LlamaIndex and a self-hosted server. | Orchestra-Research/ | 13k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 58 | Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works. | Orchestra-Research/ | 13k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 59 | Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model. | Orchestra-Research/ | 13k | 2 repos | ~2.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 60 | Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery. | Orchestra-Research/ | 13k | 2 repos | ~2.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 61 | Generates text embeddings locally with the sentence-transformers library for RAG, semantic search, clustering and similarity, with model picks for general, multilingual and legal text. | Orchestra-Research/ | 13k | 2 repos | ~1.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 62 | Trains and uses SentencePiece tokenizers on raw text, with BPE or Unigram models, for multilingual and CJK projects that need a reproducible vocabulary. | Orchestra-Research/ | 13k | 2 repos | ~1.4k | Automated safety check: Notes | MIT | 3 mo ago |
| 63 | Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads. | Orchestra-Research/ | 13k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 64 | Explains three ways to speed up LLM inference: draft-model speculative decoding, Medusa heads and lookahead decoding with Jacobi iteration, and when each one fits. | Orchestra-Research/ | 13k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 65 | Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs. | Orchestra-Research/ | 13k | 2 repos | ~2.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 66 | Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count. | Orchestra-Research/ | 13k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 67 | Trains LLMs with reinforcement learning using verl, from ByteDance's Seed team, with GRPO, PPO and other algorithms and swappable training and rollout backends. | Orchestra-Research/ | 13k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 68 | Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. | Orchestra-Research/ | 13k | 2 repos | ~3.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 69 | Covers logging and viewing training metrics, histograms, model graphs, embeddings and profiles with TensorBoard in PyTorch and TensorFlow projects. | Orchestra-Research/ | 13k | 3 repos | ~3.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 70 | Explains how to train a model to be harmless with self-critique, revision and AI-generated preference feedback, with Hugging Face and TRL code for each stage. | Orchestra-Research/ | 13k | 2 repos | ~2k | Automated safety check: Pass | MIT | 3 mo ago |
| 71 | Generates publication-quality figures for ML papers from research context. | Orchestra-Research/ | 13k | 2 repos | ~5.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 72 | Guides GRPO reinforcement-learning fine-tuning of language models with TRL, centered on designing reward functions for formats, verifiable tasks and reasoning. | Orchestra-Research/ | 13k | 3 repos | ~4.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 73 | Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support | Orchestra-Research/ | 13k | 2 repos | ~618 | Automated safety check: Pass | MIT | 3 mo ago |
| 74 | Guide to using Mamba selective state-space models for linear-time sequence modeling, from the Mamba block and pretrained checkpoints to Mamba-2 and speed comparisons. | Orchestra-Research/ | 13k | 2 repos | ~1.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 75 | Tracks ML experiments, versions models in the MLflow registry and covers deployment and reproducibility, with autologging for common frameworks. | Orchestra-Research/ | 13k | 2 repos | ~3.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 76 | Walks through nanoGPT, Karpathy's compact GPT implementation: training on Shakespeare, reproducing GPT-2, fine-tuning GPT-2 checkpoints and training on your own text. | Orchestra-Research/ | 13k | 2 repos | ~1.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 77 | Explains RWKV, a hybrid that trains in parallel like a GPT and runs inference like an RNN with constant memory per token, plus usage, fine-tuning and troubleshooting. | Orchestra-Research/ | 13k | 2 repos | ~1.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 78 | PyTorch training reference: architecture choice by data type, scaling rules, a training loop, optimizer and learning-rate choices, and fixes for loss spikes or OOM. | Orchestra-Research/ | 13k | 1 repo | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 79 | Paragraph-level blueprint for 10-12 page systems papers aimed at OSDI, SOSP, ASPLOS, NSDI and EuroSys, with page budgets, writing patterns, checklists and templates. | Orchestra-Research/ | 13k | 1 repo | ~3.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 80 | Guide to renting GPUs on Lambda Labs for ML training and inference: on-demand instances, 1-Click Clusters, SSH access, persistent filesystems and alternatives. | Orchestra-Research/ | 13k | 4 repos | ~3k | Automated safety check: Warn | MIT | 3 mo ago |
| 81 | Uses Meta's LlamaGuard moderation model to screen prompts and model replies against six safety categories, with vLLM, FastAPI and NeMo Guardrails setups. | Orchestra-Research/ | 13k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 82 | Offers ten ideation frameworks for exploring new research directions, stress-testing half-formed ideas and finding gaps when you are stuck or changing fields. | Orchestra-Research/ | 13k | 2 repos | ~4.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 83 | Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. | Orchestra-Research/ | 13k | 1 repo | ~2.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 84 | Applies cognitive science frameworks for creative thinking to CS and AI research ideation. | Orchestra-Research/ | 13k | 2 repos | ~5.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 85 | Turns papers, repositories, logs or notes into an Agent-Native Research Artifact with claims, concepts, configs, an exploration graph and grounded evidence. | Orchestra-Research/ | 13k | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 86 | Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling. | Orchestra-Research/ | 13k | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 87 | Guidance for using A-Evolve to improve an AI agent automatically, evolving its prompts, skills and memory against a benchmark through solve, observe and evolve cycles. | Orchestra-Research/ | 13k | — | ~3.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 88 | Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards. | Orchestra-Research/ | 13k | — | ~2.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 89 | Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups. | Orchestra-Research/ | 13k | — | ~3.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 90 | Fine-tunes and serves Physical Intelligence's pi0, pi0-fast and pi0.5 robot policies with JAX or PyTorch, including checkpoint conversion and policy servers. | Orchestra-Research/ | 13k | — | ~3.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 91 | Generates Beamer LaTeX PDF and editable PPTX slides from a compiled paper, with speaker notes and an optional talk script, sized to four talk lengths. | Orchestra-Research/ | 13k | — | ~2.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 92 | 92.Autoresearch Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. | Orchestra-Research/ | 13k | 2 repos | ~6.2k | Automated safety check: Warn | MIT | 3 mo ago |
| 93 | Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and… | Orchestra-Research/ | 13k | — | ~3.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 94 | Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration… | Orchestra-Research/ | 13k | — | ~4.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 95 | NVIDIA's runtime safety framework for LLM applications. An agent skill from Orchestra-Research/AI-Research-SKILLs. | Orchestra-Research/ | 13k | 2 repos | ~1.9k | Automated safety check: Warn | MIT | 3 mo ago |
| 96 | 96.Prompt Guard Meta's 86M prompt injection and jailbreak detector. An agent skill from Orchestra-Research/AI-Research-SKILLs. | Orchestra-Research/ | 13k | 1 repo | ~2.4k | Automated safety check: Warn | MIT | 3 mo ago |
