DistilBertForSequenceClassification( (distilbert): DistilBertModel( (embeddings): Embeddings( (word_embeddings): Embedding(30522, 768, padding_idx=0) (position_embeddings): Embedding(512, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (transformer): Transformer( (layer): ModuleList( (0): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) (1): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) (2): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) (3): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) (4): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) (5): TransformerBlock( (attention): MultiHeadSelfAttention( (dropout): Dropout(p=0.1, inplace=False) (q_lin): Linear(in_features=768, out_features=768, bias=True) (k_lin): Linear(in_features=768, out_features=768, bias=True) (v_lin): Linear(in_features=768, out_features=768, bias=True) (out_lin): Linear(in_features=768, out_features=768, bias=True) ) (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (ffn): FFN( (dropout): Dropout(p=0.1, inplace=False) (lin1): Linear(in_features=768, out_features=3072, bias=True) (lin2): Linear(in_features=3072, out_features=768, bias=True) (activation): GELUActivation() ) (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) ) ) ) ) (pre_classifier): Linear(in_features=768, out_features=768, bias=True) (classifier): Linear(in_features=768, out_features=3, bias=True) (dropout): Dropout(p=0.2, inplace=False) ) This is what I get when i print model. I have created bentofile.yaml and able to containerize it.But the api being generated is throwing me error.Can i get a generic service.py file for the above model?