Browse published AI skills maintained by cuba6112. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
69Repository stars across indexed skills
0Repository forks
0Average repository stars per indexed skill
0Repository stars may repeat across skills from the same repository.
High-level training framework for PyTorch that abstracts boilerplate while maintaining flexibility. Includes the Trainer, LightningModule, and support for multi-GPU scaling and reproducibility. (lightning, pyto...
Linear algebra operations in NumPy, including matrix multiplication, SVD, system solving, and least squares fitting. Triggers: linalg, matrix multiplication, SVD, eigenvalues, matrix decomposition, lstsq, multi...
Safe filesystem operations for agents, including path normalization vs resolution, temp file handling, atomic replacement, and spooled buffers. Use when reading/writing user-supplied paths, staging outputs, or...
File I/O operations including binary formats (npy/npz), text processing (csv), and memory-mapping for huge datasets. Triggers: io, load, save, npz, genfromtxt, memmap, loadtxt.
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distrib...
Fine-tuning multimodal vision-language models (Llama 3.2 Vision, Qwen2.5 VL) using optimized vision layers (triggers: vision models, multimodal, Llama 3.2 Vision, Qwen2.5 VL, UnslothVisionDataCollator, finetune...
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thi...
Deep dive into memory layout, including strides, C vs Fortran order, and zero-copy view generation via stride tricks. Triggers: strides, C-order, Fortran-order, memory locality, stride_tricks.
Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wrapping. Triggers: ufunc, vectorize, reduce, accumulate, frompyfunc, in-place.
Structured and record arrays for C-interoperability, binary blob interpretation, and multi-field tabular data handling. Triggers: structured array, record array, compound dtype, multi-field index.
Fine-tuning Speech-to-Text models like Whisper using Unsloth's optimized LoRA pipeline. Triggers: stt, whisper, transcription, audio fine-tuning, speech-to-text, audio normalization.
Protocols for cross-library data exchange including DLPack, buffer interfaces, and __array_ufunc__ for overriding NumPy functions. Triggers: DLPack, interoperability, __array_interface__, __array_ufunc__, buffe...
Asyncio patterns in Python for high-concurrency IO-bound tasks. Includes coroutines, task management, and asynchronous resource handling. Triggers: asyncio, python-async, coroutine, await, async-gather, async-g...
Computer vision library for PyTorch featuring pretrained models, advanced image transforms (v2), and utilities for handling complex data types like bounding boxes and masks. (torchvision, transforms, tvtensor,...
Modern random number generation using the Generator API, focusing on statistical properties, parallel streams, and reproducibility. Triggers: random, rng, default_rng, SeedSequence, probability distributions, s...
Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging...
Discrete Fourier Transform routines for spectral analysis, signal filtering, and frequency-domain operations. Triggers: fft, fourier transform, spectral analysis, rfft, fftshift, ifft.
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardi...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.