
Practitioner runbook for training and serving large models, from GPUs to NaN loss spikes
- Open source
- 19.7K GitHub stars
- Developer tools

Practitioner runbook for training and serving large models, from GPUs to NaN loss spikes

Search the Hugging Face Hub and run GPU jobs through the HF MCP server tools

Drive the Hugging Face Hub from the hf CLI: repos, buckets, jobs, endpoints and papers

Read the local AWS profile, region and caller identity before touching an AWS account

Plan a model deployment to Amazon SageMaker and pick the right inference pathway

Estimate GPU memory for a Hugging Face model's weights and KV cache without downloading it

Recommend top Hugging Face models for a task from official leaderboards and device limits

Explore Hugging Face datasets through the read-only Dataset Viewer API

Build Gradio web UIs, chatbots and ML demos in Python, and call Spaces from the CLI

Find GGUF models on Hugging Face, pick a quant and serve them locally with llama.cpp

Guides an agent through press outreach, pitches, press pages and crisis statements

Guides design of referral, affiliate and partner programs and review campaigns

Designs lead lifecycle, scoring, routing and pipeline rules that align marketing and sales

Creates sales decks, one-pagers, objection docs, battle cards and demo scripts for reps

Adds, fixes and validates schema.org JSON-LD markup for search engine rich results

Audits a site's crawlability, indexing, Core Web Vitals and on-page SEO for an agent

Guides agents through reviewing and improving signup, registration and trial-start flows

Plans website page hierarchy, navigation, URL structure and internal linking for a site

Plans SMS, MMS and WhatsApp marketing programs with TCPA and A2P 10DLC compliance checks

Plans and drafts organic social posts for LinkedIn, X, Instagram, TikTok and Facebook

Guides an agent through choosing and producing marketing videos with AI tools or code

Guides coding agents to build product-specific web and iOS interfaces instead of generic

Finds C# API changes that break or drift from TypeScript and JavaScript clients

Audits an iOS app's code and metadata for likely App Store rejection risks

Guides the agent through diagnosing and fixing Arch Linux problems with pacman and systemd

Generates a project architecture blueprint document by analyzing a codebase's structure

Guides designing Arduino devices that connect to Azure IoT Hub and IoT Edge

Lets an agent create, list, update and delete Arize AI LLM provider integrations

Lets your agent manage Arize annotation configs, review queues and span labels

Turns raw work history into evidence-backed impact statements for reviews and updates