hindi-bert-quantized / config.json
smsk1999's picture
Upload ElectraForSequenceClassification
260589a verified
{
"add_cross_attention": false,
"architectures": [
"ElectraForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"classifier_dropout": null,
"dtype": "float32",
"embedding_size": 128,
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 256,
"id2label": {
"0": "AMBIGUOUS",
"1": "ASSERTION",
"2": "CHALLENGE",
"3": "COURTESY",
"4": "DIRECTIVE",
"5": "QUERY",
"6": "REJECTION",
"7": "SALUTATION",
"8": "STALL",
"9": "VALIDATION"
},
"initializer_range": 0.02,
"intermediate_size": 1024,
"is_decoder": false,
"label2id": {
"AMBIGUOUS": 0,
"ASSERTION": 1,
"CHALLENGE": 2,
"COURTESY": 3,
"DIRECTIVE": 4,
"QUERY": 5,
"REJECTION": 6,
"SALUTATION": 7,
"STALL": 8,
"VALIDATION": 9
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 4,
"num_hidden_layers": 12,
"pad_token_id": 2,
"problem_type": "single_label_classification",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"type_vocab_size": 2,
"use_cache": false,
"vocab_size": 39628
}