sahajBERT-NCC / config.json
SaulLu's picture
Add tokenizer type in config.json
f9fc2ba
{
"_name_or_path": "albertvillanova/autonlp-baselines-indic_glue-multi_class_classification-1351187",
"_num_labels": 6,
"architectures": [
"AlbertForSequenceClassification"
],
"attention_probs_dropout_prob": 0,
"bos_token_id": 2,
"classifier_dropout_prob": 0.1,
"down_scale_factor": 1,
"embedding_size": 128,
"eos_token_id": 3,
"gap_size": 0,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0,
"hidden_size": 1024,
"id2label": {
"0": "kolkata",
"1": "state",
"2": "national",
"3": "sports",
"4": "entertainment",
"5": "international"
},
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 4096,
"label2id": {
"kolkata": 0,
"state": 1,
"national": 2,
"sports": 3,
"entertainment": 4,
"international": 5
},
"layer_norm_eps": 1e-12,
"max_length": 64,
"max_position_embeddings": 512,
"model_type": "albert",
"net_structure_type": 0,
"num_attention_heads": 16,
"num_hidden_groups": 1,
"num_hidden_layers": 24,
"num_memory_blocks": 0,
"pad_token_id": 0,
"padding": "max_length",
"position_embedding_type": "absolute",
"transformers_version": "4.6.1",
"type_vocab_size": 2,
"vocab_size": 32000,
"tokenizer_class": "PreTrainedTokenizerFast"
}