{ "_name_or_path": "ckpts/xlm-roberta-base-trimmed-en-50000", "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": 50002, "vocabtrimmer": { "mining_config": { "dataset": "vocabtrimmer/mc4_validation", "dataset_column": "text", "dataset_name": "en", "dataset_split": "validation", "language": "en", "min_frequency": 2, "target_vocab_size": 50000 }, "stats": { "compression_rate_embedding": 20.00063999488004, "compression_rate_full": 44.734940546186806, "parameter_size_embedding/raw": 192001536, "parameter_size_embedding/trimmed": 38401536, "parameter_size_full/raw": 278295186, "parameter_size_full/trimmed": 124495186, "vocab_size/raw": 250002, "vocab_size/trimmed": 50002 } } }