Fine-tuning LoRA

Fine-tuning Job

Fine-tuning ModelSelect the base model and provide required credentials to begin fine-tuning. Ensure the API token and database URL are valid.

Fine-tuning Model *

Please select a model

Hugging Face API Token *

Hugging Face Dataset URL *

Configure Fine-tuning JobAdd metadata and settings for your LoRA job. Accurate configuration helps improve training quality and makes your model easier to share.

Training Type

LoRA Rank *

LoRA Alpha *

LoRA Droppout *

Epochs *

Checkpoints *

Batch Size

Max Gradient Norm *