mkiani/gpt2-system

1{2  "activation_function": "gelu_new",3  "architectures": [4    "GPT2LMHeadModel"5  ],6  "attn_pdrop": 0.1,7  "bos_token_id": 50256,8  "embd_pdrop": 0.1,9  "eos_token_id": 50256,10  "initializer_range": 0.02,11  "layer_norm_epsilon": 1e-05,12  "model_type": "gpt2",13  "n_ctx": 1024,14  "n_embd": 768,15  "n_head": 12,16  "n_layer": 12,17  "n_positions": 1024,18  "resid_pdrop": 0.1,19  "summary_activation": null,20  "summary_first_dropout": 0.1,21  "summary_proj_to_labels": true,22  "summary_type": "cls_index",23  "summary_use_proj": true,24  "task_specific_params": {25    "text-generation": {26      "do_sample": true,27      "max_length": 5028    }29  },30  "vocab_size": 5025731}