albert-japanese-v2 / config.json
system's picture
system
HF staff
Update config.json
62bdb4b
{
"architectures": [
"AlbertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"classifier_dropout_prob": 0.1,
"do_sample": false,
"down_scale_factor": 1,
"embedding_size": 128,
"eos_token_ids": null,
"finetuning_task": null,
"gap_size": 0,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 3072,
"is_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"model_type": "albert",
"net_structure_type": 0,
"num_attention_heads": 12,
"num_beams": 1,
"num_hidden_groups": 1,
"num_hidden_layers": 12,
"num_labels": 2,
"num_memory_blocks": 0,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"pad_token_id": null,
"pruned_heads": {},
"repetition_penalty": 1.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"use_bfloat16": false,
"vocab_size": 32000
}