| { | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "GPTPanguForCausalLM" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 1024, | |
| "model_type": "gpt_pangu", | |
| "num_heads": 40, | |
| "num_layers": 40, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 40064, | |
| "tokenizer_class": "GPTPanguTokenizer", | |
| "auto_map": { | |
| "AutoConfig": "configuration_gptpangu.GPTPanguConfig", | |
| "AutoTokenizer": ["tokenization_gptpangu.GPTPanguTokenizer", null], | |
| "AutoModelForCausalLM": "modeling_gptpangu.GPTPanguForCausalLM" | |
| }, | |
| "pad_token_id": 6 | |
| } | |