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 Model Tuning , found 40 results

Default Newest Most Downloaded

TRL Reinforcement Fine-Tuning

fine-tuning-with-trl

Orchestra-Research/AI-Research-SKILLs

Provides TRL-based RLHF fine-tuning flows covering SFT, reward-model training, PPO, DPO, and GRPO so teams can align HuggingFace models with preferences using both pipeline scripts and CLI helpers.

Groq Cost Tuning

groq-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guide to reducing Groq inference spend by routing requests to cost-effective models, trimming token usage, caching repeated calls, batching requests, and setting spend limits for Groq Cloud billing scenarios.

Groq Performance Tuning

groq-performance-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guides developers to optimize Groq API calls through model selection, streaming, semantic caching, and parallel orchestration so latency-sensitive applications get consistent sub-100ms inference.

Half Quadratic Quantization

hqq-quantization

Orchestra-Research/AI-Research-SKILLs

Calibrate-free half-quadratic quantization for LLMs that delivers 1-8 bit model compression with configurable backends (PyTorch, TorchAO, BitBlas, Marlin). Ideal for fast quantization workflows, zero-data deployment, and PEFT/LoRA fine-tuning with HuggingFace or vLLM stacks.

Hyperparameter Tuner Assistant

hyperparameter-tuner

jeremylongshore/claude-code-plugins-plus-skills

Automated guidance for hyperparameter tuning within ML training workflows, offering best practices, production-ready code, and validation across modeling stages like data prep, training, and experiment tracking.

Ideogram Cost Tuning

ideogram-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guides selection of Ideogram models, resolutions, caching, batching, and monitoring to lower per-image credits while maintaining quality; ideal for billing analysis or budget-aware teams using Ideogram image generation.

LangChain Cost Tuning

langchain-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guides production LangChain deployments through token tracking, prompt trimming, model tiering, caching, and budget callbacks so you can monitor costs, optimize token usage, and stop overspending on LLM APIs.

LangChain Performance Tuning

langchain-performance-tuning

jeremylongshore/claude-code-plugins-plus-skills

Step-by-step guidance for benchmarking LangChain apps, enabling caching, batching, streaming, and prompt/model tuning to cut latency, boost throughput, and improve resource use when a pipeline feels slow.

Langfuse Cost Optimization

langfuse-cost-tuning

jeremylongshore/claude-code-plugins-plus-skills

Monitor Langfuse telemetry to record LLM token usage, aggregate spend by model and time, alert on budget breaches, and steer requests toward cheaper models while caching responses and trimming prompts.

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.

LLM Prompt Optimization

llm-application-dev-prompt-optimize

sickn33/antigravity-awesome-skills

Guides expert prompt engineers through advanced LLM prompt optimization techniques—constitutional AI, chain-of-thought reasoning, and model-specific tuning—to boost accuracy, reduce hallucinations, and cut token costs.

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.

Prev 123 4 Next

Language