clips/e5-large-trm
0103
1{2 "architectures": [3 "XLMRobertaModel"4 ],5 "attention_probs_dropout_prob": 0.1,6 "bos_token_id": 0,7 "classifier_dropout": null,8 "eos_token_id": 2,9 "hidden_act": "gelu",10 "hidden_dropout_prob": 0.1,11 "hidden_size": 1024,12 "initializer_range": 0.02,13 "intermediate_size": 4096,14 "layer_norm_eps": 1e-05,15 "max_position_embeddings": 514,16 "model_type": "xlm-roberta",17 "num_attention_heads": 16,18 "num_hidden_layers": 24,19 "output_past": true,20 "pad_token_id": 1,21 "position_embedding_type": "absolute",22 "torch_dtype": "float32",23 "transformers_version": "4.55.4",24 "type_vocab_size": 1,25 "use_cache": true,26 "vocab_size": 50002,27 "vocabtrimmer": {28 "mining_config": {29 "dataset": "allenai/c4",30 "dataset_column": "text",31 "dataset_name": "nl",32 "dataset_split": "validation",33 "language": "nl",34 "min_frequency": 2,35 "target_vocab_size": 5000036 },37 "stats": {38 "compression_rate_embedding": 20.00063999488004,39 "compression_rate_full": 63.42141456705587,40 "parameter_size_embedding/raw": 256002048,41 "parameter_size_embedding/trimmed": 51202048,42 "parameter_size_full/raw": 559890432,43 "parameter_size_full/trimmed": 355090432,44 "vocab_size/raw": 250002,45 "vocab_size/trimmed": 5000246 }47 }48}49 