| { | |
| "architectures": [ | |
| "BertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "tokenizer_class": "XLMRobertaTokenizer", | |
| "transformers_version": "4.56.1", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 50002, | |
| "vocabtrimmer": { | |
| "mining_config": { | |
| "dataset": "allenai/c4", | |
| "dataset_column": "text", | |
| "dataset_name": "nl", | |
| "dataset_split": "validation", | |
| "language": "nl", | |
| "min_frequency": 2, | |
| "target_vocab_size": 50000 | |
| }, | |
| "stats": { | |
| "compression_rate_embedding": 19.997840319632694, | |
| "compression_rate_full": 34.71229478768889, | |
| "parameter_size_embedding/raw": 96014208, | |
| "parameter_size_embedding/trimmed": 19200768, | |
| "parameter_size_full/raw": 117653760, | |
| "parameter_size_full/trimmed": 40840320, | |
| "vocab_size/raw": 250037, | |
| "vocab_size/trimmed": 50002 | |
| } | |
| } | |
| } | |