| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "gradient_checkpointing": false, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "output_past": true, | |
| "resid_pdrop": 0.1, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 320 | |
| } | |
| }, | |
| "tokenizer_class": "BertTokenizer", | |
| "vocab_size": 21130, | |
| "latent_dim": 256, | |
| "pad_token_id": 0 | |
| } | |