gptbert-pol-250steps-base / original_project_config.json
jumelet's picture
Add main & ema weights for pol
b6c0fbf verified
raw
history blame contribute delete
407 Bytes
{
"attention_probs_dropout_prob": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"intermediate_size": 2560,
"max_position_embeddings": 512,
"position_bucket_size": 32,
"num_attention_heads": 12,
"num_hidden_layers": 12,
"vocab_size": 16384,
"layer_norm_eps": 1e-05,
"force_causal_mask": true,
"classifier_dropout": 0.1,
"classifier_layer_norm_eps": 1e-05,
"num_labels": 2
}