|
{ |
|
"_name_or_path": "5CD-AI/viso-twhin-bert-large", |
|
"architectures": [ |
|
"BertForMaskedLM" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4096, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 24, |
|
"pad_token_id": 0, |
|
"position_embedding_type": "relative_key", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.38.2", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"vocab_size": 20002, |
|
"vocabtrimmer": { |
|
"mining_config": { |
|
"dataset": "vocabtrimmer/mc4_validation", |
|
"dataset_column": "text", |
|
"dataset_name": "en", |
|
"dataset_split": "validation", |
|
"language": "en", |
|
"min_frequency": 2, |
|
"target_vocab_size": 20000 |
|
}, |
|
"stats": { |
|
"compression_rate_embedding": 8.000735994112047, |
|
"compression_rate_full": 58.03015244164301, |
|
"parameter_size_embedding/raw": 256002048, |
|
"parameter_size_embedding/trimmed": 20482048, |
|
"parameter_size_full/raw": 561712786, |
|
"parameter_size_full/trimmed": 325962786, |
|
"vocab_size/raw": 250002, |
|
"vocab_size/trimmed": 20002 |
|
} |
|
} |
|
} |
|
|