Sebastian Husch Lee
Sebastian Husch Lee
> @sjrl Why not add a unit test for a document whose length is larger than tokenizer max_seq_len to capture the driving force behind this PR and also to the...
- [x] Add unit test using Jean-Baptiste/camembert-ner to test that "first" aggregation method works for it now (did not before)
Hi @rdubester thanks for the code snippet! Could you also provide us with the code you use to create `retrievers` and `preprocessors`?
Hi @masci, PR #3154 partially resolves this issue. The PR did not add the training and evaluation of token classification models. I can edit the text of the main issue...
Sorry, we do not actively maintain this project any longer. We migrated the core modeling parts of FARM into [Haystack](https://github.com/deepset-ai/haystack/). All active development is happening there and this repo is...
> Hi @sjrl we are planning a release in the next two weeks. Could this PR maybe make it into the new release? Did you have the chance to test...
Hey @julian-risch I first tried to get `DistributedDataParallel` to work today by turning on `distributed` training (without amp). Right now this option is hardcoded to be off since we are...
@julian-risch Yes, I completely agree.
Original discussion from private repo https://github.com/deepset-ai/haystack-private/issues/5 that is summarized above
@devinsaini I don’t believe there is work planned for that currently. I would recommend opening a new issue for that as a feature request!