diff --git a/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py b/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py index 34a037ab..47ec7072 100644 --- a/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py @@ -101,11 +101,6 @@ class FlashRWAttention(torch.nn.Module): def __init__( self, config, prefix, weights, - # num_heads, - # num_heads_kv, - # hidden_size, - # bias, - # process_group=None, reduce=True, ): super().__init__()