القائمة
Skills في هذا المستودع
جمع SkillsMP عدد ٥٬٢٦٢ من skills من TuYv/ccpm. افتح أي skill لمراجعة مصدره وتفاصيله.
TuYv/ccpmعرض ٤٠ من أصل ٥٬٢٦٢ skills مجمعة.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace,…
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
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 H100), or require tensor/pipeline/sequence/context/expert…
لغة النص الأصلي: الإنجليزية
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 speculative RL for maximum throughput.
لغة النص الأصلي: الإنجليزية
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, Muon), LR scheduling, mixed precision, debugging, and…
لغة النص الأصلي: الإنجليزية
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
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 from scratch. Train on Shakespeare (CPU) or OpenWebText…
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
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 cloud platforms. NVIDIA's enterprise-grade platform with…
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
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 distributed architecture and GPU resource sharing.
لغة النص الأصلي: الإنجليزية
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 minimal accuracy loss, or for multi-adapter serving. HuggingFace's…
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
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. Use when you want clean training loops with built-in best…
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing,…
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic…
لغة النص الأصلي: الإنجليزية
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, XLNet, mBART. Train on raw text without pre-tokenization. Use…
لغة النص الأصلي: الإنجليزية
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 inference than vLLM with prefix sharing. Powers 300,000+ GPUs…
لغة النص الأصلي: الإنجليزية
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training…
لغة النص الأصلي: الإنجليزية
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
لغة النص الأصلي: الإنجليزية
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
لغة النص الأصلي: الإنجليزية
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
لغة النص الأصلي: الإنجليزية
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
لغة النص الأصلي: الإنجليزية
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4),…
لغة النص الأصلي: الإنجليزية
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
لغة النص الأصلي: الإنجليزية
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
لغة النص الأصلي: الإنجليزية
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…
لغة النص الأصلي: الإنجليزية
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works…
لغة النص الأصلي: الإنجليزية
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
لغة النص الأصلي: الإنجليزية
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.
لغة النص الأصلي: الإنجليزية
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints,…
لغة النص الأصلي: الإنجليزية
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
لغة النص الأصلي: الإنجليزية
Update peon-ping configuration — volume, pack rotation, categories, active pack, and other settings. Use when user wants to change peon-ping settings like volume, enable round-robin, add packs to rotation, toggle sound categories, or adjust any config.
لغة النص الأصلي: الإنجليزية
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
لغة النص الأصلي: الإنجليزية