{ "vocab_size": 32000, "n_positions": 256, "n_ctx": 256, "n_embd": 512, "n_layer": 12, "n_head": 8, "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02 }