Luis Quintanilla

Results 168 comments of Luis Quintanilla
trafficstars

![image](https://user-images.githubusercontent.com/46974588/88369102-4c102300-cd5d-11ea-82ac-d3ddf766bd45.png)

![image](https://user-images.githubusercontent.com/46974588/88369557-449d4980-cd5e-11ea-813a-2ab391e64c8f.png)

![image](https://user-images.githubusercontent.com/46974588/88370144-74008600-cd5f-11ea-8273-b41dc580517f.png)

![image](https://user-images.githubusercontent.com/46974588/88370433-04d76180-cd60-11ea-8925-e4adf7ef53ea.png)

![image](https://user-images.githubusercontent.com/46974588/88371200-93001780-cd61-11ea-97e9-7fb5eabb1e94.png)

@briacht @aslotte @bartczernicki @jwood803 tagging you for visibility. It would also be great to get input from community members.

Hi @murilocurti I suspect this is your [post on StackOverflow](https://stackoverflow.com/questions/75022045/ml-net-how-to-define-shape-vectors-for-gpt2-onnx-model). Here is a [sample](https://gist.github.com/luisquintanilla/bc91de8668cfa7c3755b20329fadd027) that might help you get started. Decoding the outputs still isn't finished yet. Basically the part...

When padding data there was an error in the original sample. This should do it. Note that I'm using the LM-HEAD model instead of the standard one because that one...

@murilocurti thanks for looking into it! You're right. I totally missed that. Can you add a comment with the link to the files you used. Thank you.

Happy to help. We're learning together here 🙂