{ | |
"attention_dropout": 0.1, | |
"depth": 12, | |
"emb_dropout": 0.1, | |
"embed_dim": 768, | |
"mlp_dropout": 0.1, | |
"mlp_ratio": 4, | |
"num_heads": 12, | |
"residual_dropout": 0.1, | |
"seq_len": 1024, | |
"vocab_size": 50257 | |
} |
{ | |
"attention_dropout": 0.1, | |
"depth": 12, | |
"emb_dropout": 0.1, | |
"embed_dim": 768, | |
"mlp_dropout": 0.1, | |
"mlp_ratio": 4, | |
"num_heads": 12, | |
"residual_dropout": 0.1, | |
"seq_len": 1024, | |
"vocab_size": 50257 | |
} |