Rycen7822 huggingface-llm-trainer
When to Use
Use for LLM fine-tuning, tokenizer setup, training arguments, LoRA adapters, evaluation metrics, or Hub checkpoint publishing.
Do Not Use When
Do not use for vision-only training or simple Gradio UI work.
Required Inputs
Base model, dataset, tokenizer strategy, hardware budget, training configuration, and checkpoint destination.
Workflow
- Inspect model and dataset sizes.
- Configure tokenizer and trainer.
- Run a tiny smoke training step.
- Evaluate and save/push outputs.