hf-internal-testing/tiny-random-MarianMTModel

1{2  "_name_or_path": "temp/dummy/marian/MarianMTModel",3  "activation_dropout": 0.0,4  "activation_function": "gelu",5  "architectures": [6    "MarianMTModel"7  ],8  "attention_dropout": 0.1,9  "bos_token_id": 0,10  "classifier_dropout": 0.0,11  "d_model": 16,12  "decoder_attention_heads": 4,13  "decoder_ffn_dim": 4,14  "decoder_layerdrop": 0.0,15  "decoder_layers": 2,16  "decoder_start_token_id": 3,17  "decoder_vocab_size": 99,18  "dropout": 0.1,19  "encoder_attention_heads": 4,20  "encoder_ffn_dim": 4,21  "encoder_layerdrop": 0.0,22  "encoder_layers": 2,23  "eos_token_id": 0,24  "forced_eos_token_id": null,25  "init_std": 0.02,26  "is_encoder_decoder": true,27  "max_position_embeddings": 20,28  "model_type": "marian",29  "num_hidden_layers": 2,30  "pad_token_id": 58100,31  "scale_embedding": false,32  "share_encoder_decoder_embeddings": true,33  "torch_dtype": "float32",34  "transformers_version": "4.25.0.dev0",35  "use_cache": true,36  "vocab_size": 5810137}38