|
{ |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"GPT2LMHeadModel" |
|
], |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 50256, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 50256, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "gpt2", |
|
"n_ctx": 1024, |
|
"n_embd": 768, |
|
"n_head": 12, |
|
"n_layer": 12, |
|
"n_positions": 1024, |
|
"resid_pdrop": 0.1, |
|
"summary_activation": null, |
|
"summary_first_dropout": 0.1, |
|
"summary_proj_to_labels": true, |
|
"summary_type": "cls_index", |
|
"summary_use_proj": true, |
|
"vocab_size": 52000 |
|
} |
|
|