Ekaterina Aidova

@sbalandi can we focus on separated representation of text encoder and image encoder (convert it as 2 models) in this notebook instead of one common model? The main advantage of...

@helena-intel I suppose issue notiwith specific pytorch version, I found this thread related to your reported issue https://discuss.pytorch.org/t/failed-to-import-pytorch-fbgemm-dll-or-one-of-its-dependencies-is-missing/201969/2 and it was reported in may, when torch 2.3 released. I suppose...

@openvino-book 32B parameters model is quite huge in comparison to 1.5B, it may take some time for conversion, and this time may be significantly more than for 1.5b. From your...

@aoke79 loading model from local folder is also supported with optimum-cli, in this case command line should be: ``` optimum-cli export openvino -m --weight-format int4 --sym --group-size 128 --ratio 1.0...

Please check this notebook https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/phi-4-multimodal/phi-4-multimodal.ipynb

> I wonder why we need to keep `VLChatProcessor` instance outside the model class and if we can move it inside? not sure that I understand your question. This is...

@IlyasMoutawwakil @echarlaix could you please take a look?

> Apologies for the delay @eaidova!! We could need to make sure we are compatible with [huggingface/transformers#36053](https://github.com/huggingface/transformers/pull/36053) before merging so that we don't have any issues when transformers v4.50 is...

@IlyasMoutawwakil could you please take a look? Tests failed due to max retry issue, not related to added model

@echarlaix , I understand your position regarding remote code and agree with that, but also would like to note that besides long time waiting for reviewing, it also brings a...