Update modeling.py

modeling.py

@@ -129,8 +129,42 @@ import torch.nn as nn
 from typing import Optional, Tuple
 from transformers import PreTrainedModel
 from transformers.modeling_outputs import Seq2SeqLMOutput
-from .configuration_small_transformer import SmallTransformerConfig
 
+class SmallTransformerConfig(PretrainedConfig):
+    model_type = "small_transformer"
+
+    def __init__(
+        self,
+        vocab_size=80000,
+        d_model=256,
+        nhead=8,
+        num_encoder_layers=3,
+        num_decoder_layers=3,
+        dim_feedforward=512,
+        dropout=0.1,
+        max_position_embeddings=512,
+        pad_token_id=0,
+        bos_token_id=1,
+        eos_token_id=2,
+        use_return_dict=True,
+        **kwargs
+    ):
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            **kwargs
+        )
+        
+        self.vocab_size = vocab_size
+        self.d_model = d_model
+        self.nhead = nhead
+        self.num_encoder_layers = num_encoder_layers
+        self.num_decoder_layers = num_decoder_layers
+        self.dim_feedforward = dim_feedforward
+        self.dropout = dropout
+        self.max_position_embeddings = max_position_embeddings
+        self.use_return_dict = use_return_dict
 
 class SmallTransformerPreTrainedModel(PreTrainedModel):
     config_class = SmallTransformerConfig