top | item 38662766 (no title) vermaat | 2 years ago Works great, does indeed have more Dutch knowledge besides only speaking Dutch. discuss order hn newest erijgersberg|2 years ago It sure does! There's still lots of room for improvement though. It still has trouble sometimes with the industry-standard Bassie en Adriaan-test.It's too bad that there is still a distinct lack of suitable Dutch training sets and benchmarks. vermaat|2 years ago I hope the 13,5 million Euro funds will be used wisely for the GPT-NL project. It would be nice if they open-source it (or at least the training dataset).
erijgersberg|2 years ago It sure does! There's still lots of room for improvement though. It still has trouble sometimes with the industry-standard Bassie en Adriaan-test.It's too bad that there is still a distinct lack of suitable Dutch training sets and benchmarks. vermaat|2 years ago I hope the 13,5 million Euro funds will be used wisely for the GPT-NL project. It would be nice if they open-source it (or at least the training dataset).
vermaat|2 years ago I hope the 13,5 million Euro funds will be used wisely for the GPT-NL project. It would be nice if they open-source it (or at least the training dataset).
erijgersberg|2 years ago
It's too bad that there is still a distinct lack of suitable Dutch training sets and benchmarks.
vermaat|2 years ago