LanguageModelZLossConfig¶
Module: fast_llm.layers.language_model.loss.config
Variant of: LanguageModelLossConfig — select with type: z_loss
Inherits from: LanguageModelLossConfig
Fields¶
weight—core-
Type:
floatDefault:1.0Weight for this loss in the total loss computation.
logits_scale_factor—feature-
Type:
floatDefault:1.0Extra logits scale factor applied for this loss only, stacked on top of the model's
logits_scale_factor. use_triton—expert-
Type:
boolorNoneDefault:NoneEnable triton implementation. Default: use if available.