gpt-font88-26 / config.json
terryspitz's picture
Training in progress steps 499
8e1f1f4
raw
history blame contribute delete
560 Bytes
{
"afn": "gelu",
"architectures": [
"OpenAIGPTLMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 1080,
"embd_pdrop": 0.1,
"eos_token_id": 1080,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "openai-gpt",
"n_embd": 768,
"n_head": 12,
"n_layer": 12,
"n_positions": 512,
"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,
"transformers_version": "4.42.4",
"vocab_size": 1081
}