|
{ |
|
"_name_or_path": "model", |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"GPTNeoForCausalLM" |
|
], |
|
"attention_dropout": 0, |
|
"attention_layers": [ |
|
"global", |
|
"local", |
|
"global", |
|
"local", |
|
"global", |
|
"local", |
|
"global", |
|
"local" |
|
], |
|
"attention_types": [ |
|
[ |
|
[ |
|
"global", |
|
"local" |
|
], |
|
4 |
|
] |
|
], |
|
"bos_token_id": 50256, |
|
"classifier_dropout": 0.1, |
|
"embed_dropout": 0, |
|
"eos_token_id": 50256, |
|
"gradient_checkpointing": false, |
|
"hidden_size": 256, |
|
"initializer_range": 0.02, |
|
"intermediate_size": null, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "gpt_neo", |
|
"num_heads": 16, |
|
"num_layers": 8, |
|
"resid_dropout": 0, |
|
"summary_activation": null, |
|
"summary_first_dropout": 0.1, |
|
"summary_proj_to_labels": true, |
|
"summary_type": "cls_index", |
|
"summary_use_proj": true, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.35.2", |
|
"use_cache": true, |
|
"vocab_size": 50257, |
|
"window_size": 256 |
|
} |
|
|