| { |
| "src_vocab": "dummy", |
| "tgt_vocab": "dummy", |
| "data": {}, |
| "share_vocab": true, |
| "training": { |
| "compute_dtype": "fp32" |
| }, |
| "model": { |
| "architecture": "transformer_encoder_scorer", |
| "scoring_type": "comet", |
| "class_identifier": "regression_metric", |
| "requires_reference": true, |
| "pretrained_model": "Unbabel/wmt22-comet-da", |
| "pool": "avg", |
| "layer": "mix", |
| "layer_transformation": "sparsemax", |
| "layer_norm": false, |
| "input_segments": [ |
| "mt", |
| "src", |
| "ref" |
| ], |
| "hidden_sizes": [ |
| 3072, |
| 1024 |
| ], |
| "activations": "Tanh", |
| "final_activation": null, |
| "dropout": 0.1, |
| "encoder_architecture": "XLMRobertaForMaskedLM", |
| "embeddings": { |
| "embedding_type": "roberta", |
| "src_word_vec_size": 1024, |
| "tgt_word_vec_size": 1024, |
| "word_vec_size": 1024, |
| "position_encoding_type": "Learned", |
| "n_positions": 514, |
| "position_shift": 0, |
| "embedding_layer_norm": true, |
| "token_type_vocab_size": 1 |
| }, |
| "encoder": { |
| "encoder_type": "transformer", |
| "layers": 24, |
| "hidden_size": 1024, |
| "heads": 16, |
| "transformer_ff": 4096, |
| "mlp_activation_fn": "gelu", |
| "layer_norm": "standard", |
| "norm_eps": 1e-05, |
| "add_qkvbias": true, |
| "add_key_bias": true, |
| "add_final_linear_bias": true, |
| "add_ffnbias": true, |
| "position_encoding_type": "Learned", |
| "n_positions": 514, |
| "encoder_layer_style": "postnorm", |
| "final_encoder_layer_norm": false |
| } |
| } |
| } |
