Skills dans ce dépôt
SkillsMP a collecté 12 131 skills depuis GrayCodeAI/starling. Ouvrez un skill pour examiner sa source et ses détails.
GrayCodeAI/starlingAffichage de 40 skills collectés sur 12 131.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking trainin...
Langue du texte source : anglais
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 beyo...
Langue du texte source : anglais
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 ...
Langue du texte source : anglais
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H...
Langue du texte source : anglais
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 s...
Langue du texte source : anglais
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 su...
Langue du texte source : anglais
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...
Langue du texte source : anglais
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Langue du texte source : anglais
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 s...
Langue du texte source : anglais
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), improv...
Langue du texte source : anglais
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or ena...
Langue du texte source : anglais
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architecture...
Langue du texte source : anglais
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture ...
Langue du texte source : anglais
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...
Langue du texte source : anglais
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or clou...
Langue du texte source : anglais
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang...
Langue du texte source : anglais
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 model...
Langue du texte source : anglais
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 adapti...
Langue du texte source : anglais
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distribute...
Langue du texte source : anglais
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-w...
Langue du texte source : anglais
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt....
Langue du texte source : anglais
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minima...
Langue du texte source : anglais
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring productio...
Langue du texte source : anglais
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for produ...
Langue du texte source : anglais
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or in...
Langue du texte source : anglais
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 HuggingF...
Langue du texte source : anglais
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...
Langue du texte source : anglais
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. ...
Langue du texte source : anglais
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange inter...
Langue du texte source : anglais
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scala...
Langue du texte source : anglais
Skill: research-ray-data
Langue du texte source : anglais
Skill: research-ray-train
Langue du texte source : anglais
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 p...
Langue du texte source : anglais
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploratio...
Langue du texte source : anglais
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, O...
Langue du texte source : anglais
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable feature...
Langue du texte source : anglais
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object mas...
Langue du texte source : anglais
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, an...
Langue du texte source : anglais
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, X...
Langue du texte source : anglais
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster i...
Langue du texte source : anglais