ADFLER-albert-base-v2 / config.json
swardiantara's picture
Upload AlbertForTokenClassification
ddbb9e2 verified
raw
history blame
1.26 kB
{
"_name_or_path": "experiments/llm-based/albert-base-v2_15",
"architectures": [
"AlbertForTokenClassification"
],
"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": 768,
"id2label": {
"0": "O",
"1": "B-Event",
"2": "I-Event",
"3": "E-Event",
"4": "S-Event",
"5": "B-NonEvent",
"6": "I-NonEvent",
"7": "E-NonEvent",
"8": "S-NonEvent"
},
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 3072,
"label2id": {
"B-Event": 1,
"B-NonEvent": 5,
"E-Event": 3,
"E-NonEvent": 7,
"I-Event": 2,
"I-NonEvent": 6,
"O": 0,
"S-Event": 4,
"S-NonEvent": 8
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "albert",
"net_structure_type": 0,
"num_attention_heads": 12,
"num_hidden_groups": 1,
"num_hidden_layers": 12,
"num_memory_blocks": 0,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.24.0",
"type_vocab_size": 2,
"vocab_size": 30000
}