huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tas...
This skill ships only metadata — no inline instructions. See the source repo for details.
Install this skill
One command (all agents)
Runs the npx skills CLI which auto-detects every AI coding agent you have installed (Claude Code, Cursor, Codex, OpenCode, Windsurf, Copilot, and 51 more).
npx skills add https://github.com/huggingface/trl/tree/main/examples/scripts\u003c/a\u003e\u003c/p\u003e\n\u003ch3\u003eFindingAlternative: shorthand form
npx skills add huggingface/trl --skill huggingface-llm-trainerInstall to a specific agent
Pick the agent you use. The CLI writes the skill to that agent's standard skill directory.
npx skills add huggingface/trl --skill huggingface-llm-trainer --agent claude-codenpx skills add huggingface/trl --skill huggingface-llm-trainer --agent cursornpx skills add huggingface/trl --skill huggingface-llm-trainer --agent codexnpx skills add huggingface/trl --skill huggingface-llm-trainer --agent opencodenpx skills add huggingface/trl --skill huggingface-llm-trainer --agent github-copilotnpx skills add huggingface/trl --skill huggingface-llm-trainer --agent windsurfManual install (no CLI)
Prefer to skip the CLI? Clone the repo and drop the skill folder into your agent's skills directory.
git clone https://github.com/huggingface/trl.gitcp -r trl/examples/scripts\u003c/a\u003e\u003c/p\u003e\n\u003ch3\u003eFinding ~/.claude/skills/ For other agents, replace ~/.claude/skills/ with their skill directory — see the full list.
Use it
Once installed, ask your agent to "use the huggingface-llm-trainer skill" or describe what you want (e.g. "Train or fine-tune language and vision models using TRL (Transformer Reinforceme"). Most agents auto-discover the skill from its SKILL.md description — no slash command needed.
npx skills. Skill files are MIT-style permissive by default — check the source repo for the actual license.
SKILL.md source
--- name: huggingface-llm-trainer description: Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training method ---
Want the ready-to-ship business bundle?
500+ agent skills, $15 one-time, lifetime access. 20 categories spanning content, marketing, sales, finance, legal, ops, SEO & more — finished deliverables, not drafts. Works with Claude Code, Codex, Cursor & every agent runtime.
Related skills 6
microsoft-foundry
Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve agent instruc...
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
azure-deploy
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "p...
azure-diagnostics
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, troubleshoot functions, troubleshoot AKS, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource...
azure-resource-lookup
List, find, and show Azure resources across subscriptions or resource groups. Handles prompts like "list the websites in my subscription", "list my web apps", "show my app services", "list virtual machines", "list my VMs", "show storage accounts", "find container apps", and "what resources do I have". USE FOR: list websites, list web apps, list app services, show websites in subscription, resource inventory, find resources by tag, tag analysis, orphaned resource discovery (not for cost analys...
azure-resource-visualizer
Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. WHEN: create architecture diagram, visualize Azure resources, show resource relationships, generate Mermaid diagram, analyze resource group, diagram my resources, architecture visualization, resource topology, map Azure infrastructure.