Tanmay patil comments

Results 7 comments of


                                            Tanmay patil

Add support for BLIP and GIT in image-to-text and VQA pipelines

@NielsRogge is this issue still open to contribute . I would like to work on it

Add support for BLIP and GIT in image-to-text and VQA pipelines

Hey @NielsRogge , I was working on VQA pipeline for BLIP but i am confused how can i give `pixel_values` to `_forward` method in `VisualQuestionAnsweringPipeline` [(src)](https://github.com/Tanmaypatil123/transformers/blob/main/src/transformers/pipelines/visual_question_answering.py#L19) because BLIP requires pixel...

Make all Transformer models compatible with model parallelism

Is there any remaining model on which I can work ? Thanks .

Tools support in ChatCompletion endpoints

Does that mean we should implement something similar to OpenAI's Assistant API? Like code interpreter, retreival, etc., right?

ValueError: min() arg is an empty sequence

Thanks @louistiti I will try this ...

ValueError: min() arg is an empty sequence

> Hey @Tanmaypatil123 Did it work? yes .. i was creating `.list` file using my custom script which was wrong .. try to use `preprocess_text.py`.

Sentence Transformers Candidate Models

@NirantK Hey, I think `fastembed` is dependent on the huggingface's tokenizer, right? Why does it not support any of the models mentioned in the issue description by default?