unslothai / unsloth

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory
https://unsloth.ai
Apache License 2.0
18.42k stars 1.29k forks source link

Adding a custom model #1096

Closed HARISHSENTHIL closed 1 month ago

HARISHSENTHIL commented 1 month ago

Hi everyone,

I recently fine-tuned a large language model (LLM) using Unsloth, and I now want to further fine-tune the same model with additional data.

How can i do that ?

danielhanchen commented 1 month ago

@HARISHSENTHIL You can reload the save model, skip get_peft_model and continue training! See https://github.com/unslothai/unsloth/wiki#loading-lora-adapters-for-continued-finetuning

HARISHSENTHIL commented 1 month ago

thank you