| { | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "finetuning_task": null, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "n_ctx": 1024, | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_layer": 24, | |
| "n_positions": 1024, | |
| "n_special": 0, | |
| "num_labels": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_past": true, | |
| "predict_special_tokens": true, | |
| "pruned_heads": {}, | |
| "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, | |
| "torchscript": false, | |
| "use_bfloat16": false, | |
| "vocab_size": 50257 | |
| } | |