| { |
| "activation_dropout": 0.0, |
| "activation_function": "relu", |
| "architectures": [ |
| "MarianForCausalLM" |
| ], |
| "attention_dropout": 0, |
| "bos_token_id": 1, |
| "d_model": 1024, |
| "decoder_attention_heads": 8, |
| "decoder_ffn_dim": 8192, |
| "decoder_layerdrop": 0.1, |
| "decoder_layers": 12, |
| "decoder_start_token_id": 1, |
| "decoder_vocab_size": 8000, |
| "dropout": 0.1, |
| "encoder_attention_heads": 16, |
| "encoder_ffn_dim": 4096, |
| "encoder_layerdrop": 0.0, |
| "encoder_layers": 12, |
| "eos_token_id": 2, |
| "forced_eos_token_id": 2, |
| "init_std": 0.0, |
| "is_decoder": true, |
| "is_encoder_decoder": false, |
| "max_length": 512, |
| "max_position_embeddings": 256, |
| "model_type": "marian", |
| "normalize_embedding": false, |
| "num_hidden_layers": 12, |
| "pad_token_id": 3, |
| "scale_embedding": true, |
| "share_encoder_decoder_embeddings": false, |
| "static_position_embeddings": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.39.3", |
| "use_cache": false, |
| "vocab_size": 8000 |
| } |
|
|
