Menu
Skills dans ce dépôt
SkillsMP a collecté 101 skills depuis math-inc/OpenGauss. Ouvrez un skill pour examiner sa source et ses détails.
math-inc/OpenGaussAffichage de 40 skills collectés sur 101.
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.
Langue du texte source : anglais
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 alignments, handle padding/truncation. Integrates seamlessly with…
Langue du texte source : anglais
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,…
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, NSFW detection. Scales across GPUs with RAPIDS. Use for…
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 features, analyzing superposition, or studying monosemantic…
Langue du texte source : anglais
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
Langue du texte source : anglais
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 GPU requirements.
Langue du texte source : anglais
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Langue du texte source : anglais
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
Langue du texte source : anglais
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on…
Langue du texte source : anglais
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules,…
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.ai's structured generation library
Langue du texte source : anglais
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),…
Langue du texte source : anglais
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,…
Langue du texte source : anglais
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
Langue du texte source : anglais
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning.…
Langue du texte source : anglais
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for…
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 masks in an image.
Langue du texte source : anglais
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
Langue du texte source : anglais
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace…
Langue du texte source : anglais
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Langue du texte source : anglais
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports…
Langue du texte source : anglais
Build, test, and debug Gauss Agent RL environments for Atropos training. Covers the GaussAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when…
Langue du texte source : anglais
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
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 minimal accuracy loss, or for multi-adapter serving. HuggingFace's…
Langue du texte source : anglais
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
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. Use when you want clean training loops with built-in best…
Langue du texte source : anglais
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Langue du texte source : anglais
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or…
Langue du texte source : anglais
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure…
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 production RAG, recommendation systems, or semantic search at…
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 scalable vector storage with Rust-powered performance.
Langue du texte source : anglais
Read, search, and create notes in the Obsidian vault.
Langue du texte source : anglais
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via Python. Uses OAuth2 with automatic token refresh. No external binaries needed — runs entirely with Google's Python client libraries in the Gauss venv.
Langue du texte source : anglais