Top Rated

The most starred skills loved by the community. Quality guaranteed!

Showing 2377-2400 of 52148 skills
Orchestra-Research

mamba-architecture

by Orchestra-Research

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Code Gen 11.2K 8mo ago
Orchestra-Research

llama-factory

by Orchestra-Research

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

ML Ops 11.2K 8mo ago
Orchestra-Research

ray-train

by Orchestra-Research

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Automation 11.2K 5mo ago
Orchestra-Research

modal-serverless-gpu

by Orchestra-Research

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Cloud 11.2K 8mo ago
Orchestra-Research

rwkv-architecture

by Orchestra-Research

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

ML Ops 11.2K 8mo ago
Orchestra-Research

transformer-lens-interpretability

by Orchestra-Research

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Automation 11.2K 7mo ago
Orchestra-Research

huggingface-tokenizers

by Orchestra-Research

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.

Git & VCS 11.2K 8mo ago
Orchestra-Research

deepspeed

by Orchestra-Research

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

ML Ops 11.2K 8mo ago
Orchestra-Research

optimizing-attention-flash

by Orchestra-Research

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Automation 11.2K 8mo ago
Orchestra-Research

llama-cpp

by Orchestra-Research

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.

CLI Tools 11.2K 8mo ago
Orchestra-Research

awq-quantization

by Orchestra-Research

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

ML Ops 11.2K 8mo ago
Orchestra-Research

gptq

by Orchestra-Research

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.

ML Ops 11.2K 8mo ago
Orchestra-Research

nnsight-remote-interpretability

by Orchestra-Research

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Debugging 11.2K 7mo ago
Orchestra-Research

nemo-guardrails

by Orchestra-Research

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Code Review 11.2K 8mo ago
Orchestra-Research

autoresearch

by Orchestra-Research

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Code Gen 11.2K 4mo ago
Orchestra-Research

verl-rl-training

by Orchestra-Research

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Agents 11.2K 6mo ago
Orchestra-Research

pytorch-fsdp2

by Orchestra-Research

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Code Gen 11.2K 6mo ago
Orchestra-Research

pyvene-interventions

by Orchestra-Research

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Git & VCS 11.2K 7mo ago
Orchestra-Research

grpo-rl-training

by Orchestra-Research

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Processing 11.2K 8mo ago
Orchestra-Research

prompt-guard

by Orchestra-Research

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Prompts 11.2K 5mo ago
Orchestra-Research

nemo-curator

by Orchestra-Research

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Processing 11.2K 8mo ago
dagger

dagger-design-proposals

by dagger

Write design proposals for Dagger features. Use when asked to draft, review, or iterate on Dagger design documents, RFCs, or proposals.

API Dev 16.1K 5mo ago
browseros-ai

write-docs

by browseros-ai

Write BrowserOS feature documentation. Use when the user wants to create or update documentation for a BrowserOS feature. This skill explores the codebase to understand features and writes concise Mintlify MDX docs.

Code Gen 12.8K 6mo ago
MoonshotAI

gen-changelog

by MoonshotAI

Generate changelog entries for code changes.

Code Gen 11K 5mo ago