reading-bird / config.json
shjwudp's picture
Upload model
773b1f6
raw
history blame
921 Bytes
{
"_name_or_path": "/cephfs/changjianbin/github.com/shjwudp/transformers/examples/pytorch/language-modeling/reading-bird/checkpoint-14000",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.0,
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 1,
"initializer_range": 0.014,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 1024,
"n_head": 16,
"n_inner": null,
"n_layer": 24,
"n_positions": 1024,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"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": "ByT5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.22.2",
"use_cache": true,
"vocab_size": 384
}