telugu-bert / config.json
nadellaroshni's picture
Training in progress, epoch 1
0145242 verified
raw
history blame
871 Bytes
{
"_name_or_path": "l3cube-pune/telugu-bert",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 768,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "Non-Hate",
"1": "Hate"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"Hate": 1,
"Non-Hate": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 197285
}