bumchik2's picture
Upload AlbertForSequenceClassification
bf0db75 verified
{
"_name_or_path": "train-albert-base-v2/checkpoint-10764",
"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": 768,
"id2label": {
"0": "Computer Science",
"1": "Economics",
"2": "Electrical Engineering and Systems Science",
"3": "Mathematics",
"4": "Physics",
"5": "Quantitative Biology",
"6": "Quantitative Finance",
"7": "Statistics"
},
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 3072,
"label2id": {
"Computer Science": 0,
"Economics": 1,
"Electrical Engineering and Systems Science": 2,
"Mathematics": 3,
"Physics": 4,
"Quantitative Biology": 5,
"Quantitative Finance": 6,
"Statistics": 7
},
"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",
"problem_type": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.48.3",
"type_vocab_size": 2,
"vocab_size": 30000
}