| { | |
| "activation_function": "gelu_new", | |
| "architectures": ["GPT2LMHeadModel"], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 2, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 3, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-5, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_layer": 12, | |
| "n_positions": 512, | |
| "pad_token_id": 0, | |
| "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, | |
| "tokenizer": "default", | |
| "transformers_version": "4.5.1", | |
| "vocab_size": 16000 | |
| } | |