rugpt2-paraphraser / config.json
{
"_name_or_path": "/home/jovyan/gpt2_large_bbpe_v50",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 1280,
"n_head": 20,
"n_inner": null,
"n_layer": 36,
"n_positions": 1024,
"output_past": true,
"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": 50257
}