{ "activation_function": "gelu", "architectures": [ "ImageGPTForCausalImageModeling" ], "attn_pdrop": 0.1, "embd_pdrop": 0.1, "gradient_checkpointing": false, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "imagegpt", "n_embd": 32, "n_head": 4, "n_inner": 37, "n_layer": 5, "n_positions": 1024, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.28.0.dev0", "type_vocab_size": 16, "use_cache": true, "vocab_size": 513 }