| { | |
| "architectures": [ | |
| "GPT1ForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "configuration_gpt1.GPT1Config", | |
| "AutoModelForCausalLM": "modeling_gpt1.GPT1ForCausalLM" | |
| }, | |
| "embd_pdrop": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 512, | |
| "model_type": "gpt1", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "resid_pdrop": 0.1, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.1", | |
| "vocab_size": 40478 | |
| } | |