← Back to context Comment by __MatrixMan__ 9 hours ago Agreed, "distilled variants" might be more suitable. 1 comment __MatrixMan__ Reply overfeed 7 hours ago Calling them variants is also inaccurate when the pretrained base and architecture are completely different.
overfeed 7 hours ago Calling them variants is also inaccurate when the pretrained base and architecture are completely different.
Calling them variants is also inaccurate when the pretrained base and architecture are completely different.