Fred Turkington

Get SQLite Working

9

I love what you're doing here with this pattern. What are the big barriers to getting SQLite working?

Fine_tune_BLIP2_on_an_image_captioning_dataset_PEFT.ipynb loss is all NaN

25

peft/Fine_tune_BLIP2_on_an_image_captioning_dataset_PEFT.ipynb This notebook: https://github.com/huggingface/notebooks/blob/main/peft/Fine_tune_BLIP2_on_an_image_captioning_dataset_PEFT.ipynb Trains fine on Google Colab at https://colab.research.google.com/drive/16XbIysCzgpAld7Kd9-xz-23VPWmqdWmW?usp=sharing#scrollTo=upI97XEH6EKe using Python 3.10.12, Torch 2.1.0 It does not train on my workstation - the loss collapses to NaN after...

Support Kosmos-2

1

https://huggingface.co/microsoft/kosmos-2-patch14-224 Used in the following fashion with `AutoModelForVision2Seq` ``` from transformers import AutoModelForVision2Seq, AutoProcessor model = AutoModelForVision2Seq.from_pretrained("microsoft/kosmos-2-patch14-224") processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224") ```

Update for compatibility with RGBASM 0.8.0

3

The syntax for `EQU` and `MACRO` have changed in RGBASM v 0.8 now, lines with EQU must start with DEF, see for example this commit: https://github.com/ISSOtm/gb-starter-kit/commit/aa5d9a7a4344343436ded80de27da7bcdb2dfb15 Likewise, the `MACRO` syntax...