I try your example Kaggle Mistral 7b Unsloth notebook. The only thing I changed - I changed Flase to True in this line:
if True: model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
As a result I am always getting error: OSError: [Errno 28] No space left on device.
I try your example
Kaggle Mistral 7b Unsloth notebook
. The only thing I changed - I changed Flase to True in this line:if True: model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
As a result I am always getting error:
OSError: [Errno 28] No space left on device
.Please see here https://www.kaggle.com/code/brand17/kaggle-mistral-7b-unsloth-notebook/log?scriptVersionId=179659896