fmikaelian

When deploying master branch on heroku app with no [`Procfile`](https://devcenter.heroku.com/articles/procfile): ``` -----> Python app detected -----> Installing python-3.6.9 -----> Installing pip -----> Installing SQLite3 -----> Installing requirements with pip Collecting...

@huggingface just released their new update, so we started to explore XLNet for cdQA (PR #205)

@tholor I updated the README with a ⛔ [NOT MAINTAINED] message and mentionned your repository as an alternative in #363 Wishing you the best to continue the open-source question-answering adventure!...

Hi @TobiKoledoye The pdf converter tutorial currently works, you can try it [here.](https://mybinder.org/v2/gh/cdqa-suite/cdQA/master?filepath=examples%2Ftutorial-use-pdf-converter.ipynb) Can you share the code you used and your pdf file so we can reproduce the bug?

We were actually discussing about this idea with @andrelmfarias a few days ago :-) It would be great to be able to define a `cdQA` pipeline like this: ```python QAPipeline(retriever='BM25',...

You have to fit the pipeline retriever to the dataframe with the documents before calling the `predict()` function: `cdqa_pipeline.fit_retriever(df=df)`

Might be a problem with the length of your answers in the json dataset. For example, do you have empty answers?

`ValueError` during evaluation after training: ```python-traceback Traceback (most recent call last): File "tutorial-train-xlnet-squad.py", line 39, in out_eval, final_prediction = reader.evaluate(X='dev-v2.0.json') ValueError: too many values to unpack (expected 2) ```

To use the XLNet reader with a pretrained `.bin` model: ```python import wget from cdqa.reader.reader_sklearn import Reader wget.download(url='https://github.com/cdqa-suite/cdQA/releases/download/XLNet_cased_vCPU/pytorch_model.bin', out='.') # cast Reader class with train params reader = Reader(model_type='xlnet', model_name_or_path='xlnet-base-cased',...

- hardware: GeForce RTX 208 - training time: 9 hours