bigBird_AAE_bio / config.json
ucabqfe's picture
add model
a5dde8c
{
"_name_or_path": "drive/MyDrive/job/820986.undefined/models/Z29vZ2xlL2JpZ2JpcmQtcm9iZXJ0YS1iYXNlX2ZpbmFs",
"architectures": [
"BigBirdForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"attention_type": "block_sparse",
"block_size": 64,
"bos_token_id": 1,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu_new",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 4096,
"model_type": "big_bird",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_random_blocks": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"rescale_embeddings": false,
"sep_token_id": 66,
"torch_dtype": "float32",
"transformers_version": "4.18.0",
"type_vocab_size": 2,
"use_bias": true,
"use_cache": true,
"vocab_size": 50358
}