config.json

{
  "architectures": [
    "Seq2SeqCrossFormer"
  ],
  "bos_token_id": 1,
  "d_ff": 1024,
  "d_model": 256,
  "dropout": 0.1,
  "eos_token_id": 2,
  "model_size": 10731266,
  "model_type": "custom_transformer",
  "n_heads": 8,
  "n_layers": 2,
  "pad_token_id": 0,
  "router_dim": 10,
  "sequence_length": 256,
  "source_sequence_dimension": 70,
  "target_sequence_dimension": 306,
  "torch_dtype": "float32",
  "transformers_version": "4.48.1",
  "vocab_size_src": 258,
  "vocab_size_tgt": 258
}