Some models deviate so much from standard transformer encoder/decoders (e.g. DeBERTa and Falcon old architecture) that we probably should not support them in mainline Curated Transformers to avoid cluttering the abstractions too much (it's curated after all). Though it would still be nice to provide official support for these models. Consider an add-on package for these models.
Probably requires #346.
Some models deviate so much from standard transformer encoder/decoders (e.g. DeBERTa and Falcon old architecture) that we probably should not support them in mainline Curated Transformers to avoid cluttering the abstractions too much (it's curated after all). Though it would still be nice to provide official support for these models. Consider an add-on package for these models.
Probably requires #346.