{ "model_type": "gpt2", "vocab_size": 50257, "n_positions": 1024, "n_ctx": 1024, "n_embd": 1600, "n_layer": 48, "n_head": 32, "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-5 }