{ "activation_function": "gelu", "architectures": [ "TFGPT2LMHeadModel" ], "attn_pdrop": 0.0, "bos_token_id": 50256, "embd_pdrop": 0.0, "eos_token_id": 50256, "gradient_checkpointing": false, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 2560, "n_head": 32, "n_inner": null, "n_layer": 32, "n_positions": 1024, "pad_token_id": 0, "resid_pdrop": 0.0, "summary_activation": null, "summary_first_dropout": 0.0, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": { "text-generation": { "do_sample": true, "max_length": 120 } }, "tokenizer_class": "XLNetTokenizer", "use_cache": true, "vocab_size": 30000 }