XueMoonLit

Results 6 comments of XueMoonLit

Error When fine-tuning from others model.bin : File "~/fairseq/fairseq/checkpoint_utils.py", line 581, in _upgrade_state_dict {"criterion_name": "CrossEntropyCriterion", "best_loss": state["best_loss"]} KeyError: 'best_loss'

Hi, I came across similar issue before, I think it's caused by the difference of checkpoint file. The checkpoint file saved by fairseq is a 'dict' variable with keys such...

Error When fine-tuning from others model.bin : File "~/fairseq/fairseq/checkpoint_utils.py", line 581, in _upgrade_state_dict {"criterion_name": "CrossEntropyCriterion", "best_loss": state["best_loss"]} KeyError: 'best_loss'

> > Reference > > @XueMoonLit Do you have a codesnippet of how you achieved this? Hi, I modified some code of function "_upgrade_state_dict" in checkpoint_utils.py, just add some keys...

Why do different -max_tokens during inference affect the prediction results？

Hi, have you found out what's wrong with this? I think, the document says that param "--max-tokens" represents max tokens per batch, suppose batch size is 64 and num of...

TypeError: forward() missing 1 required positional argument: 'prev_output_tokens'

I think it's caused by data preprocess, you can check your preprocess step whether bugs occured at that time, you can also tracing the change of "sample" object in code...

[Question]: container ragflow-mysql is unhealthy

Any updates?

[Question]: container ragflow-mysql is unhealthy

> I have met similar issue with WSL2 Ubuntu 22.04, I built ragflow docker image with source code using "git clone https://github.com/infiniflow/ragflow.git". I tried my best to build image successfully,...