{ "afn": "gelu", "attn_pdrop": 0.1, "embd_pdrop": 0.1, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "n_ctx": 512, "n_embd": 768, "n_head": 12, "n_layer": 12, "n_positions": 512, "n_special": 0, "resid_pdrop": 0.1, "vocab_size": 40478 }