-
Hi @Nicous20 and everyone,
While going through the test sample and annotations, I found that the ground truth start and end time stamps are not matching with the test sample duration.
, it only returns the True/False prediction and its score (as model.Distribution objects). It may be the case that more than one, or none, of the languages are chosen as…
-
Projects like CodeT5 use masked span prediction for better context understanding. Do you think this will be necessary?
-
Hello,
Firstly, thanks you all for your work.
I am struggling to understand how to fine-tune T5.
In #113, it is mentionned that there are 2 eos tokens (one for encoder, one for decoder). How…
-
Right now, `skweak` supports two main types of NLP tasks: (token-level) sequence labelling and text classification. Both rests on the idea that labelling functions associate labels to *text spans*, an…
-
Pose your questions as Issue Comments (below) for Marc Berman regarding his 10/10 talk on "Implicit racial biases are lower in more populous more diverse and less segregated US cities".
**_Abstrac…
-
The existing documentation has several issues:
https://docs.ragas.io/en/latest/howtos/integrations/langchain.html
1. The imports are wrong see https://github.com/explodinggradients/ragas/issues/57…
-
Would you consider adding the ability to include Octopus Agile predictions? It would be especially useful to have predicted rates for a day or two in the future.
This data is already easy to get in…
-
There is a 500 error happening somewhere in the Comprehension module. The pod logs showed this:
```prediction = self.model.predict(passage=str(X[0]), question=str(X[1]))['best_span_str'] IndexErro…
-
In the output of `split_parser`, `split` and `parser` we have an output of tokens and predictions.
It may be worth considering a different type of output with the spans of each reference/token rath…