As the title said, I want to merge my PEFT LoRA adapter model ( ArcturusAI/Crystalline-1.1B-v23.12-tagger ) that I trained before with the base model ( TinyLlama/TinyLlama-1.1B-Chat-v0.6 ) and make a fully new model. And I got this code from ChatGPT: from transformers import AutoModel, AutoConfig # L…

merge_and_unload is not compatible with SafeTensors, only with bin files and OP doesn’t seem to have adapters in bin format.

I also encounter this problem, may I ask have you worked it out?

I have a working code in my repo (Phi-2).

I want to merge my PEFT adapter model with the base model and make a fully new model

accOne996795 January 21, 2024, 5:36am 2

Have you tried the method merge_and_unload from PeftModel ad shown in this thread Help with merging LoRA weights back into base model :-) - #7 by accOne996795

Topic		Replies	Views
I wonder how to merge my PEFT adapter with the base model and finally get a new whole model? 🤗Transformers	27	1798	February 7, 2025
Cannot Merge Lora weights back to the base model Intermediate	8	564	October 29, 2024
Help with merging LoRA weights back into base model :-) Beginners	11	72783	February 6, 2025
How do I merge a lora adapter back into the model weights? Beginners	1	3236	August 23, 2023
Merging in successive loras to a base model Beginners	2	1371	October 25, 2024