|
{ |
|
"_name_or_path": "/cache/stage1_trained_models_300M/iter_0500000_hf/", |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"PanguAlphaModel" |
|
], |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 1, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 2, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "gpt2", |
|
"n_embd": 1024, |
|
"n_head": 16, |
|
"n_inner": 4096, |
|
"n_layer": 24, |
|
"n_positions": 1024, |
|
"reorder_and_upcast_attn": false, |
|
"resid_pdrop": 0.1, |
|
"scale_attn_by_inverse_layer_idx": false, |
|
"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, |
|
"tokenizer_class": "_JIEBATokenizer", |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.19.0", |
|
"use_cache": true, |
|
"vocab_size": 64007 |
|
} |
|
|