Agent skills by Orchestra-Research, page 2

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

Orchestra-Research/AI-Research-SKILLs

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.

Orchestra-Research/AI-Research-SKILLs

High-performance RLHF framework with Ray+vLLM acceleration. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Uses Ray Data to read, transform and write large datasets across a cluster for ML training and batch inference, with streaming execution and optional GPU steps.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

Generates publication-quality figures for ML papers from research context.

Orchestra-Research/AI-Research-SKILLs

Multi-agent orchestration framework for autonomous AI collaboration.

Orchestra-Research/AI-Research-SKILLs

Framework for building LLM-powered applications with agents, chains, and RAG.

Orchestra-Research/AI-Research-SKILLs

Data framework for building LLM applications with RAG. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Covers logging and viewing training metrics, histograms, model graphs, embeddings and profiles with TensorBoard in PyTorch and TensorFlow projects.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Guides GRPO reinforcement-learning fine-tuning of language models with TRL, centered on designing reward functions for formats, verifiable tasks and reasoning.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Tracks ML experiments, versions models in the MLflow registry and covers deployment and reproducibility, with autologging for common frameworks.

Orchestra-Research/AI-Research-SKILLs

Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing.

Orchestra-Research/AI-Research-SKILLs

Turns papers, repositories, logs or notes into an Agent-Native Research Artifact with claims, concepts, configs, an exploration graph and grounded evidence.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Applies cognitive science frameworks for creative thinking to CS and AI research ideation.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

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/AI-Research-SKILLs

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture.

Orchestra-Research/AI-Research-SKILLs

Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.

Orchestra-Research/AI-Research-SKILLs

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/AI-Research-SKILLs

NVIDIA's runtime safety framework for LLM applications. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs

Meta's 86M prompt injection and jailbreak detector. An agent skill from Orchestra-Research/AI-Research-SKILLs.

Orchestra-Research/AI-Research-SKILLs