Download

Skill UI

Browse and discover 5066+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Modal , found 18 results

Default Newest Most Downloaded

AWQ Weight Quantization

awq-quantization

Orchestra-Research/AI-Research-SKILLs

AWQ provides activation-aware 4-bit quantization for large language models, delivering ~3x inference speedup and sub-5% accuracy loss to deploy instruction-tuned or multimodal models on memory-constrained GPUs with vLLM integration and Marlin kernels.

Axolotl Fine-Tuning Guide

Orchestra-Research/AI-Research-SKILLs

Guides developers through Axolotl-based LLM fine-tuning, covering YAML config patterns, LoRA/QLoRA and DPO/KTO/ORPO/GRPO workflows, FSDP tips, compressed checkpoints, and debugging best practices for reliable multimodal training.

Axolotl Fine-Tuning Guide

Orchestra-Research/AI-Research-SKILLs

Guides developers through Axolotl-based LLM fine-tuning, covering YAML config patterns, LoRA/QLoRA and DPO/KTO/ORPO/GRPO workflows, FSDP tips, compressed checkpoints, and debugging best practices for reliable multimodal training.

Azure Content Understanding

azure-ai-contentunderstanding-py

sickn33/antigravity-awesome-skills

Azure AI Content Understanding SDK for Python orchestrates multimodal extraction from documents, images, audio, and video to feed RAG pipelines or automate structured workflows.

Azure Content Understanding

azure-ai-contentunderstanding-py

sickn33/antigravity-awesome-skills

Azure AI Content Understanding SDK for Python orchestrates multimodal extraction from documents, images, audio, and video to feed RAG pipelines or automate structured workflows.

BLIP-2 Vision Language

blip-2-vision-language

Orchestra-Research/AI-Research-SKILLs

BLIP-2 is a vision-language pre-training framework that links frozen image encoders with LLMs to generate captions, answer visual questions, perform image-text retrieval, and drive multimodal chat with strong zero-shot accuracy.

CLIP Vision-Language

Orchestra-Research/AI-Research-SKILLs

OpenAI's CLIP links vision and language for zero-shot image classification, semantic search, content moderation, and cross-modal retrieval without fine-tuning, making it ideal for pipelines needing fast image-text matching or vector search.

Llama Factory Guide

Orchestra-Research/AI-Research-SKILLs

Provides expert guidance for fine-tuning large language models with LLaMA-Factory, covering no-code WebUI usage, QLoRA/LoRA optimizations, multimodal inputs, and curated references so developers can build and debug solutions faster.

Enterprise Miles RL

miles-rl-training

Orchestra-Research/AI-Research-SKILLs

Guidance for training large multimodal MoE models with miles, covering FP8/INT4 quantization-aware regimes, train-inference alignment, speculative RL throughput tricks, and enterprise stability practices for production deployments.

Modal Serverless GPU

modal-serverless-gpu

Orchestra-Research/AI-Research-SKILLs

Modal's serverless GPU cloud platform lets teams run ML training, inference, and batch jobs with pay-per-second pricing, automatic scaling, Python-native infra definitions, fast cold starts, and container caching.

OpenAI Automation Toolkit

openai-automation

ComposioHQ/awesome-claude-skills

Automate OpenAI API workflows through the Composio MCP integration, covering text and multimodal responses with structured outputs, embeddings, image generation, and model discovery.

Sentence Transformers Embeddings

sentence-transformers

Orchestra-Research/AI-Research-SKILLs

High-quality Sentence Transformers framework that ships 5000+ pretrained models for multilingual, multimodal, and domain-specific embeddings; ideal for RAG, semantic search, clustering, and production vector stores without relying on external APIs.

Language