| { | |
| "_name_or_path": "ckpts/xlm-roberta-base-trimmed-pt-60000", | |
| "architectures": [ | |
| "XLMRobertaForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "xlm-roberta", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 60002, | |
| "vocabtrimmer": { | |
| "mining_config": { | |
| "dataset": "vocabtrimmer/mc4_validation", | |
| "dataset_column": "text", | |
| "dataset_name": "pt", | |
| "dataset_split": "validation", | |
| "language": "pt", | |
| "min_frequency": 2, | |
| "target_vocab_size": 60000 | |
| }, | |
| "stats": { | |
| "compression_rate_embedding": 24.00060799513604, | |
| "compression_rate_full": 47.49819351887747, | |
| "parameter_size_embedding/raw": 192001536, | |
| "parameter_size_embedding/trimmed": 46081536, | |
| "parameter_size_full/raw": 278295186, | |
| "parameter_size_full/trimmed": 132185186, | |
| "vocab_size/raw": 250002, | |
| "vocab_size/trimmed": 60002 | |
| } | |
| } | |
| } | |