Download

Skill UI

Browse and discover 5115+ curated skills

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

Search Transformer , found 19 results

Default Newest Most Downloaded

Neural Network Builder

building-neural-networks

jeremylongshore/claude-code-plugins-plus-skills

Enables Claude to configure neural network architectures through the neural-network-builder plugin, creating or modifying models and defining layers, activation functions, and training parameters whenever network design or tuning is requested.

GPTQ LLM Quantization

Orchestra-Research/AI-Research-SKILLs

Post-training 4-bit quantization for LLMs that trims memory by 4× with minimal perplexity loss, enabling 70B+ models to run faster on consumer GPUs while integrating with transformers, PEFT, and QLoRA workflows.

Fast NLP Tokenizers

huggingface-tokenizers

Orchestra-Research/AI-Research-SKILLs

Rust-powered HuggingFace tokenizers deliver <20s per GB speed, trainable BPE/WordPiece/Unigram models, alignment tracking, padding, and transformers integration for production NLP pipelines.

Long Context Extensions

Orchestra-Research/AI-Research-SKILLs

Extends transformer models’ context windows using RoPE, YaRN, ALiBi, and interpolation so LLMs can process documents of 32k–128k+ tokens, extrapolate to longer lengths, and deploy efficient positional encodings and bias strategies for fine-tuning or inference.

Mamba Selective State Models

mamba-architecture

Orchestra-Research/AI-Research-SKILLs

Mamba provides selective state-space models with O(n) inference complexity, letting you handle million-token sequences faster than transformers while skipping KV caches and benefiting from a hardware-aware design. Use it for long-context language modeling, streaming applications, and scalable low-memory sequence learners.

Minimalist GPT Training

Orchestra-Research/AI-Research-SKILLs

NanoGPT is a hackable ~300-line PyTorch reproduction of GPT-2 for learning transformer internals; train Shakespeare or OpenWebText on CPUs or multi-GPU setups, experiment with fine-tuning/custom datasets, and prototype quickly.

Clinical AI SDK Patterns

openevidence-sdk-patterns

jeremylongshore/claude-code-plugins-plus-skills

Guides building clinical AI integrations with the OpenEvidence SDK, covering singleton client setup, typed query builders, response transformers, and caching strategies for reliable decision support.

Flash Attention Optimization

optimizing-attention-flash

Orchestra-Research/AI-Research-SKILLs

Speeds up transformer attention with Flash Attention techniques, offering 2-4× throughput gains and 10-20× memory reduction. Ideal for long-context models on PyTorch (native or flash-attn lib), H100 FP8, and sliding window scenarios to resolve GPU memory bottlenecks and improve inference.

Structured Text Generation

Orchestra-Research/AI-Research-SKILLs

Outlines guarantees valid JSON/XML/code generation via CFG-driven FSM filtering, Pydantic schemas, and fast local or API models (Transformers, vLLM, llama.cpp), making structured inference safe and high-performance.

Pyspark Transformer Guide

pyspark-transformer

jeremylongshore/claude-code-plugins-plus-skills

Automated assistance for pyspark transformer work within data pipelines, activating when you request transformer patterns or best practices and covering ETL, data transformation, orchestration, and streaming scenarios.

LLM Quantization Toolkit

quantizing-models-bitsandbytes

Orchestra-Research/AI-Research-SKILLs

Quantizes LLMs to 8-bit or 4-bit to cut memory by 50-75%, letting inference and QLoRA fine-tuning run on constrained GPUs while keeping accuracy high; supports Bitsandbytes, NF4/INT8 formats, 8-bit optimizers, and HuggingFace Transformers.

Response Transformer Assistance

response-transformer

jeremylongshore/claude-code-plugins-plus-skills

Auto-activating API Integration skill that guides response transformer work, covering common patterns, third-party APIs, webhooks, SDK generation, and delivers best-practice code plus validation advice.

Language