Closed jaidhyani closed 2 months ago
~Currently the minimal viable fix. Further simplification is possible and desirable.~
Fixes and simplifies training data generation. There's no longer a separate label tensor, since *ForCausalLM models shift the labels internally (for some reason)
~Currently the minimal viable fix. Further simplification is possible and desirable.~
Fixes and simplifies training data generation. There's no longer a separate label tensor, since *ForCausalLM models shift the labels internally (for some reason)