minskiter's picture
feat(model): update model parameters
57034b1
{
"_name_or_path": "minskiter/cossim-bert-chinese-wwm-ext",
"architectures": [
"CosSimBertModel"
],
"tokenizer_class": "BertTokenizer",
"custom_pipelines": {
"sentences_sim": {
"impl": "minskiter/cossim-bert-chinese-wwm-ext--similar.SimilarPipeline",
"pt": "AutoModel",
"tf": []
},
"textencode": {
"impl": "minskiter/cossim-bert-chinese-wwm-ext--similar.EncodePipeline",
"pt": "AutoModel",
"tf": []
}
},
"auto_map":{
"AutoModel": "minskiter/cossim-bert-chinese-wwm-ext--modeling_bert.CosSimBertModel",
"AutoConfig": "minskiter/cossim-bert-chinese-wwm-ext--configuration_bert.SimBertConfig"
},
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "simbert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.30.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 21128
}