Pedro Cuenca

In terms of user expectations, if `--local-dir` is specified then it sounds reasonable to me that the global cache is not required. Totally agree with keeping the current behaviour in...

I just tested commit 0588d7cab707a8952c4433137ec70a49d864fe2b and the same error occurs. Trying to debug.

Hi @seboslaw! I've recently done a similar exercise, and discovered that if the model accepts flexible shapes, then Core ML only uses the CPU. In the case of sequence-to-sequence models...

> I've tried your suggestion (I think I did :) and updated the upperBounds of the input parameters Sorry, I think I wasn't clear. I didn't mean to make the...

Testing T5 is high up in my to-do list, I hope to get to it pretty soon and hopefully I'll have some insight then :) Sorry for the no-answer though.

@seboslaw What you tried to do [here](https://github.com/huggingface/exporters/issues/33#issuecomment-1547815946) used to work, but in newer versions of Core ML it results in the error you've seen. The problem is that the model...

@seboslaw This is the branch: https://github.com/huggingface/exporters/pull/37. I have other local changes, so I hope I didn't break or miss anything. I verified that T5 encoder and decoder export with fixed...

Hi @fakerybakery! I think the easiest way is to use this automated Space, which uses `exporters` under the hood: https://huggingface.co/spaces/huggingface-projects/transformers-to-coreml You enter the model id (`facebook/m2m100_418M`), then select the task...

> I can't convert 70b on this @USBhost did you try with `convert-hf-to-gguf.py`?

> Doesn't seem that the `eos_token` is working with either of the convert scripts in this PR @m18coppola the instruct models use two different EOS tokens: the standard one (``),...