Update configuration_opt.py

configuration_opt.py

@@ -56,6 +56,7 @@ class OPTConfig(PretrainedConfig):
         do_layer_norm_before (`bool`, *optional*, defaults to `True`):
 
             Whether to perform layer normalization before the attention block.
+
         word_embed_proj_dim (`int`, *optional*):
             `word_embed_proj_dim` can be set to down-project word embeddings, *e.g.* `opt-350m`. Defaults to
             `hidden_size`.
@@ -115,7 +116,7 @@ class OPTConfig(PretrainedConfig):
         eos_token_id=2,
         enable_bias=True,
         layer_norm_elementwise_affine=True,
-        attn_implementation='eager',
+        #attn_implementation='eager',
         **kwargs,
     ):
         super().__init__(