Add the link to the QA model to huggingface#122
Open
espoirMur wants to merge 1 commit intomicrosoft:mainfrom
Open
Add the link to the QA model to huggingface#122espoirMur wants to merge 1 commit intomicrosoft:mainfrom
espoirMur wants to merge 1 commit intomicrosoft:mainfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I have converted the QA checkpoint model to a Huggingface model! Please, have a look and test If it works.
The full model is here: https://huggingface.co/espoir/BioGPT-Large-QA-PubMedQA!
Canvas:
The main prompt model was outputting a sequence of words learned1, learned2, ... learned9 before output the answer of the question! I checked this my be due to the way prompt was set up during training.
Before adding the model to huggingface and to make it work I have added 9 extras words to the embedding layers to accommodate the fairseq model weight.
With that below are the difference output of the two models:
FairseqOne:
The one with hugginface: