Edoardo Procino

bug in segmentation/mmcv_custom/checkpoint.py

3

Hi, I found a bug in the checkpoint.py file.

Not able to solve RuntimeError: Unsloth: Please file a bug report! Error patching SFTTrainer

3

Hi everybody! I used unsloth for the first time a couple of weeks ago and was very happy with it! In particular, I used it to perform a fine tutoring...

Problems using evaluation

2

Hi! I'm fine tuning gemma2:9B, but the train stops and returns the following error if I add an evaluation dataset. This training for ancient greek to italian translations, some weeks...

Vast.ai implementation

2

Hi! I wanted to ask if you have a guide for using unsloth on vast, it would be great to be able to use it as I sometimes have memory...

[Bug] Qwen3: Evaluation loss doesn't work! (works only at step 0)

1

I was trying to fine tune qwen3, and I tried **unsloth/Qwen3-4B-unsloth-bnb-4bit**. I used a dataset of mine about greek to italian translations (I used the same dataset for other models...

[Bug] Impossible to convert Gemma3 4b into gguf

13

I tried to save my fine-tuned gemma3 on HuggingFace in gguf format, I followed the unsloth's notebook but I have the following error when I run model.save_pretrained_merged("gemma-3-finetune", tokenizer) NotImplementedError: Unsloth:...