large model release, would you update it?

[chikiuso]

hi I see the large model of gpt2 and the pretrained dialogpt based on it is released, would you consider include in this project? thanks!

[polakowo]

Yes, I'm going to update the package to the new transformers version soon.

[chikiuso]

thanks a lot :D

[ghost]

Yeah, that would be awesome !

[polakowo]

I released a new version that accepts any text generation model, including large dialogpt (use model = microsoft/DialoGPT-large in chatbot.cfg).

[ghost]

@polakowo

I made a fork and added Dockerfiles with GPU/CPU support. It works awesome !

Would be awesome to use it with the deeppavlov-agent...

Thanks again !

[polakowo]

@lucmichalski looks great! I had a Dockerfile previously but it downloaded the same model every time I deployed the container, which made it too expensive to play with. Maybe I should have synced caching dirs to avoid this.

[ghost]

@polakowo

do you want me to do a PR ? I used a docker volume for the model

I made some modifications to the worktree https://github.com/lucmichalski/gpt2bot