configs/top_transformer_120M.json

{
    "attention_bias": false,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "fuse_cross_entropy": true,
    "fuse_norm": false,
    "hidden_act": "swish",
    "hidden_size": 768,
    "initializer_range": 0.02,
    "max_position_embeddings": 4096,
    "model_type": "top_transformer",
    "num_heads": 12,
    "num_hidden_layers": 14,
    "norm_eps": 1e-06,
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 32000,
    "use_top_loss": true,
    "top_window_size": 2048
}