jbeno's picture
Initial model files and config for custom ELECTRA Large classifier for sentiment
bccac83
{
"architectures": [
"ElectraClassifier"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"dropout_rate": 0.3,
"embedding_size": 1024,
"hidden_act": "gelu",
"hidden_activation": "SwishGLU",
"hidden_dim": 1024,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "negative",
"1": "neutral",
"2": "positive"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"negative": 0,
"neutral": 1,
"positive": 2
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_layers": 2,
"pad_token_id": 0,
"pooling": "mean",
"position_embedding_type": "absolute",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.37.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}