{ "vocab_size": 50257, "context_length": 256, "emb_dim": 768, "n_heads": 12, "n_layers": 12, "drop_rate": 0.1, "qkv_bias": false, "max_length": 256, "output_dimension": 768, "batch_size": 8, "architectures": [ "GPTModel" ], "model_type": "gpt2", "n_positions": 256, "n_embd": 768, "n_layer": 12, "n_head": 12, "activation_function": "gelu_new", "resid_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "bos_token_id": 50256, "eos_token_id": 50256 }