Closed mathis-lambert closed 8 months ago
Since you are using full fine-tuning, you can just skip the check for peft model by commenting the call of is_adapter_model
.
@huchinlp yep I just noticed it and i dont want to skip this step.
The issue has been fixed with the #49 PR thanks to @dmilcevski
But yes it seems ok now DPO Alignment is running ! thanks 🙏
Hi,
I'm using Alignment-Handbook to finetune mistral on a custom dataset. I've made the SFT Full Fine Tuning and it ended up well, and saved my pretrained model to ./data/zephyr-7b-sft-full. Now i want to align my model with DPO, everything is okay with the loading of the dataset but it's impossible to load the pretrained model saved on my local machine. Althought i've tried with absolute and relative path, it always throw this error :
and no matter how much I change, nothing happens.
Here is the /dpo/config_full.yaml file :
Please help :)