Evals?
#3
by
Athrael
- opened
There's currently no evals, or benchmarks for this model. I'd expect a bit more from Apple 😁
Ah, they did release this script- https://github.com/apple/ml-clara/blob/main/evaluation/evaluate.py
and this related data- https://github.com/apple/ml-clara/tree/main/evaluation/evaluation_data
Which look to match up with the reported datasets in Table 3 from the paper