Plugins
12 plugins@samyakjhaveri
Research
Research from SamyakJhaveri/loam.
18 skills · plugin
@brycewang-stanford
Auto Empirical Research Skills
Auto Empirical Research Skills from brycewang-stanford/Auto-Empirical-Research-Skills.
86 skills · plugin
curated
Deep Research Report
For analysts and researchers needing comprehensive, evidence-backed reports with citations.
11 skills · plugin
@phuryn
Market Research
Market research skills for PMs: user personas, market segmentation, sentiment analysis, and competitive analysis.
7 skills · plugin
@owl-listener
Design Research
User research skills for designers: personas, empathy maps, journey maps, interview scripts, usability testing, and card sorting.
12 skills · plugin
@alirezarezvani
Research Ops
Enterprise / cross-functional Research Operations domain — the managed counterpart to the academic research/ domain. v2.9.0 ships 5 skills: orchestrator (context: fork) + clinical-research (study design: protocol synopsis + endpoint selection + sample-size/power for means/proportions/survival + phase-gate feasibility) + research-finance (R&D program budgeting with F&A split + burn/runway + capital
5 skills · plugin
curated
Market Research Report
Install this pack to produce a decision-oriented market research report with competitive analysis, market sizing, and source attribution.
7 skills · plugin
curated
Company Research Profile
Install this pack to build and manage a company research profile with fundamentals, valuation bands, red flags, and events.
4 skills · plugin
curated
User Persona from Research
Install this pack to create detailed, actionable user personas from research data with jobs-to-be-done and behavioral insights.
5 skills · plugin
@testdouble
Han Research
Pre-planning knowledge-work skills for the Han suite: understanding a problem before anyone commits to a plan. Home of research, gap-analysis, and issue-triage, plus the research-analyst agent. Depends on han-communication and han-core; bundled by the han meta-plugin.
3 skills · plugin
@brycewang-stanford
25 HosungYou Diverga
25 HosungYou Diverga from brycewang-stanford/Auto-Empirical-Research-Skills.
32 skills · plugin
@brycewang-stanford
42 Wanshuiyin ARIS
42 Wanshuiyin ARIS from brycewang-stanford/Auto-Empirical-Research-Skills.
38 skills · plugin
Results for “research”
60 skills
orchestra-research Sparse Autoencoder Training
Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.
10.4k · bundle
majiayu000 Jax
High-performance numerical computing with JAX, covering functional transformations, Flax NNX, and best practices for ML research.
567 · bundle
orchestra-research Sentencepiece
Train and use SentencePiece tokenizers for multilingual NLP, supporting BPE and Unigram algorithms with raw Unicode text.
10.4k · bundle
orchestra-research Tensorrt LLM
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency on NVIDIA GPUs (A100/H100).
10.4k · bundle
orchestra-research Mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow.
10.4k · bundle
orchestra-research Tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance using TensorBoard.
10.4k · bundle
More results
orchestra-research Grpo Rl Training
Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.
10.4k · bundle
orchestra-research Axolotl
Provides expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, and multimodal support.
10.4k · bundle
orchestra-research Rwkv Architecture
Use RWKV, a linear-time RNN-Transformer hybrid, for efficient long-context inference and training with constant memory usage.
10.4k · bundle
orchestra-research Implementing Llms Litgpt
Train, fine-tune, and deploy LLMs using LitGPT's clean implementations of 20+ architectures like Llama, Gemma, and Phi.
10.4k · bundle
orchestra-research Llamaguard
Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.
10.4k
orchestra-research Experiment Tracking Swanlab
Track ML experiments with open-source run logging, local or self-hosted dashboards, and media visualization using SwanLab.
10.4k · bundle
orchestra-research Simpo Training
Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.
10.4k · bundle
orchestra-research Mamba Architecture
Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.
10.4k · bundle
orchestra-research Nanogpt
Train and experiment with a minimal GPT implementation in ~300 lines of PyTorch, from character-level Shakespeare to GPT-2 scale.
10.4k · bundle
orchestra-research Moe Training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.
10.4k · bundle
orchestra-research Nnsight Remote Interpretability
Run interpretability experiments on neural network internals using nnsight, with optional NDIF remote execution for massive models.
10.4k · bundle
orchestra-research Modal Serverless Gpu
Run ML workloads on Modal's serverless GPU cloud platform with auto-scaling, pay-per-second pricing, and Python-native infrastructure.
10.4k · bundle
orchestra-research Fine Tuning With Trl
Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.
10.4k · bundle
orchestra-research Unsloth
Provides expert guidance for fast fine-tuning with Unsloth, including LoRA/QLoRA optimization, with 2-5x faster training and 50-80% less memory usage.
10.4k · bundle
orchestra-research Miles Rl Training
Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.
10.4k · bundle
orchestra-research Skypilot Multi Cloud Orchestration
Run ML training and batch jobs across multiple clouds with automatic cost optimization, spot instance recovery, and unified orchestration.
10.4k · bundle
orchestra-research Pyvene Interventions
Perform causal interventions on PyTorch models using pyvene's declarative framework for causal tracing, activation patching, and interchange intervention training.
10.4k · bundle
orchestra-research Openrlhf Training
Train large language models (7B-70B+) with RLHF using PPO, GRPO, DPO, and other algorithms, accelerated by Ray and vLLM for distributed multi-GPU setups.
10.4k · bundle
orchestra-research Weights And Biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B.
10.4k · bundle
orchestra-research Deepspeed
Provides expert guidance for distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, and sparse attention.
10.4k · bundle
orchestra-research Huggingface Accelerate
Add distributed training support to any PyTorch script with minimal code changes using a unified API for DDP, DeepSpeed, FSDP, and mixed precision.
10.4k · bundle
orchestra-research Long Context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques for processing long documents and implementing efficient positional encodings.
10.4k · bundle
orchestra-research Speculative Decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.
10.4k · bundle
orchestra-research Slime Rl Training
Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.
10.4k · bundle
orchestra-research Awq Quantization
Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.
10.4k · bundle
orchestra-research Llama Factory
Provides expert guidance for fine-tuning LLMs with LLaMA-Factory, covering WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, and multimodal support.
10.4k · bundle
orchestra-research Training Llms Megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.
10.4k · bundle
orchestra-research Evaluating Llms Harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.
10.4k · bundle
orchestra-research Peft Fine Tuning
Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.
10.4k · bundle
orchestra-research Gguf Quantization
Convert and quantize models to GGUF format for efficient CPU/GPU inference with llama.cpp, supporting 2-8 bit quantization and Apple Silicon acceleration.
10.4k · bundle