Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.
12928 results
(97.5ms)
page 61 / 647
nemo-curator
0.00
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16Γ faster), quality filtering (30+ heuristics), semantic deduplication, PII...
using-superpowers
0.00
Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring...
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+...
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...
model-pruning
0.00
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...
gguf-quantization
0.00
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without...
hqq-quantization
0.00
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when...
making-waffles
0.00
Generates WAFFLES Declarations for social media posts β preemptive lists of what a post does NOT say. Use when users mention WAFFLES, ask for clarifications on their post, want to prevent...
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...
long-context
0.00
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...
rwkv-architecture
0.00
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,...
moe-training
0.00
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5Γ cost reduction vs dense models), implementing sparse...
fine-tuning-with-trl
0.00
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,...
ray-data
0.00
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...
aptos
0.00
Aptos blockchain and Move language expert. Covers Move programming (abilities, generics, resources), Aptos framework modules, smart contract development, token standards (Coin, Fungible Asset,...
executing-plans
0.00
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...
grpo-rl-training
0.00
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid...