| { |
| "architectures": [ |
| "XLMRobertaModel" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 0, |
| "classifier_dropout": null, |
| "dtype": "float32", |
| "eos_token_id": 2, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 514, |
| "model_type": "xlm-roberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "transformers_version": "4.57.0", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 32768, |
| "vocabtrimmer": { |
| "mining_config": { |
| "dataset": "lbourdois/fineweb-2-trimming", |
| "dataset_column": "text", |
| "dataset_name": "spa", |
| "dataset_split": "train", |
| "language": "spa", |
| "min_frequency": 2, |
| "target_vocab_size": 32766 |
| }, |
| "stats": { |
| "compression_rate_embedding": 13.107095143238853, |
| "compression_rate_full": 60.24853369361119, |
| "parameter_size_embedding/raw": 256002048, |
| "parameter_size_embedding/trimmed": 33554432, |
| "parameter_size_full/raw": 560142482, |
| "parameter_size_full/trimmed": 337477632, |
| "vocab_size/raw": 250002, |
| "vocab_size/trimmed": 32768 |
| } |
| } |
| } |
|
|
