| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPTNeoForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_layers": ["global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local"], | |
| "attention_types": [ | |
| [ | |
| ["global", "local"], | |
| 16 | |
| ] | |
| ], | |
| "bos_token_id": 50256, | |
| "embed_dropout": 0.0, | |
| "eos_token_id": 50256, | |
| "gradient_checkpointing": false, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neo", | |
| "num_heads": 20, | |
| "num_layers": 32, | |
| "resid_dropout": 0.0, | |
| "vocab_size": 50257, | |
| "use_cache": true, | |
| "window_size": 256 | |
| } |