Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Huggingface Llm Trainer

Skill Verifiziert Aktiv

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 tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Zweck

Streamline and simplify the process of training and converting LLMs on cloud infrastructure, making advanced ML workflows accessible.

Funktionen

  • Fine-tune LLMs using TRL or Unsloth
  • Leverage Hugging Face Jobs infrastructure
  • Supports SFT, DPO, GRPO, and Reward Modeling
  • Convert models to GGUF format for local deployment
  • Includes cost estimation and Trackio monitoring

Anwendungsfälle

  • Fine-tune language models on cloud GPUs without local setup
  • Align models with human preferences using DPO
  • Convert trained models to GGUF for Ollama or LM Studio
  • Optimize training for limited GPU memory with Unsloth

Nicht-Ziele

  • Directly managing Hugging Face infrastructure (handled by `hf-cli`)
  • Advanced distributed training setup beyond TRL's automatic handling
  • Modifying the core TRL or Unsloth libraries

Installation

/plugin install skills@huggingface-skills

Qualitätspunktzahl

Verifiziert
99 /100
Analysiert about 19 hours ago

Vertrauenssignale

Letzter Commit2 days ago
Sterne10.5k
LizenzApache-2.0
Status
Quellcode ansehen

Ähnliche Erweiterungen