Receber por email
← Voltar para o catálogo

Autor no catálogo

braxtonROSE4

123 skills 861 estrelas no total GitHub ↗

Skills publicadas

Mostrando 12 de 123

simpo-training

7

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 than DPO/PPO.

DevOps e Infra #ai #llm por braxtonROSE4

docker-management

7

Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.

DevOps e Infra #ai #docker por braxtonROSE4

pytorch-fsdp

7

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Dados e Análise #ai por braxtonROSE4

neuroskill-bci

7

Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app running locally.

Design e Frontend #ai por braxtonROSE4

manim-video

7

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any program

Dados e Análise #ai por braxtonROSE4

huggingface-hub

7

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Dados e Análise #ai #deploy por braxtonROSE4

pokemon-player

7

Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.

DevOps e Infra #ai por braxtonROSE4

whisper

7

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Escrita e Conteúdo #ai por braxtonROSE4

instructor

7

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Dados e Análise #ai #llm por braxtonROSE4

heartmula

7

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

Outros #ai por braxtonROSE4

blackbox

7

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Design e Frontend #ai #api por braxtonROSE4

siyuan

7

SiYuan Note API for searching, reading, creating, and managing blocks and documents in a self-hosted knowledge base via curl.

Documentos #ai #api por braxtonROSE4