deberta-v3-xsmall / generator_config.json
Pengcheng He
Add generator
43d13d5
raw
history blame
593 Bytes
{
"model_type": "deberta-v2",
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"initializer_range": 0.02,
"intermediate_size": 1536,
"max_position_embeddings": 512,
"relative_attention": true,
"position_buckets": 256,
"norm_rel_ebd": "layer_norm",
"share_att_key": true,
"pos_att_type": "p2c|c2p",
"layer_norm_eps": 1e-7,
"max_relative_positions": -1,
"position_biased_input": false,
"num_attention_heads": 6,
"num_hidden_layers": 6,
"z_steps": 2,
"type_vocab_size": 0,
"vocab_size": 128100
}