M. Yusuf Sarıgöz

Thanks @JustinLin610! Yes, let me clarify it: - HF native generator works well with all the HF-compatible variants. - Original Fairseq decoder works well with all the Fairseq-compatible variants. -...

Hi @JustinLin610, congrats on the awesome work. > and we'll soon release the one for HF transformers, Do you have any any update in this? @NohTow: > No, the model...

Ok I quickly had a look at it and for the base-sized checkpoint ~100 parameters out of 965 have different names. I'll try to make a conversion tomorrow --it's definitely...

I managed to convert weights from Fairseq version to Transformers-compatible one. Here's a [PR on HF Hub](https://huggingface.co/OFA-Sys/OFA-base-caption/discussions/1) for the base version --I'm also making another PR for the large size...

There's no HF model repo for OFA-large-caption, so I couldn't make a PR. Instead, I uploaded the converted model to [my storage for public download](https://storage.googleapis.com/mys-released-models/OFA-large-caption.zip).

> I’ll test it on monday and try to reproduce the paper results. Cool. I'd like to hear about the results of your tests as well. I'll also share the...

And here comes the huge-sized image-captioning model. [Download, zipped, 2.39 GB](https://storage.googleapis.com/mys-released-models/OFA-huge-caption.zip).

And here's the [Colab notebook with explanations](https://colab.research.google.com/drive/1LLJewY92LXdeug5m_ceMUHdlqrRQwSQJ?usp=sharing) that I used for conversion.

> generate gibberish before the eos token Yes, I also noticed it. I haven't checked whether the authors did something particular for it, but I postprocessed my caption result as...

> I guess it is hurting the performance in the end Don't think so. As previously stated, most of the Seq2Seq models have this behavior. I also observed it in...