lagodw/plotly_gpt2_large

1{2  "_name_or_path": "gpt2-large",3  "activation_function": "gelu_new",4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 50256,9  "embd_pdrop": 0.1,10  "eos_token_id": 50256,11  "initializer_range": 0.02,12  "layer_norm_epsilon": 1e-05,13  "model_type": "gpt2",14  "n_ctx": 1024,15  "n_embd": 1280,16  "n_head": 20,17  "n_inner": null,18  "n_layer": 36,19  "n_positions": 1024,20  "resid_pdrop": 0.1,21  "scale_attn_weights": true,22  "summary_activation": null,23  "summary_first_dropout": 0.1,24  "summary_proj_to_labels": true,25  "summary_type": "cls_index",26  "summary_use_proj": true,27  "task_specific_params": {28    "text-generation": {29      "do_sample": true,30      "max_length": 5031    }32  },33  "torch_dtype": "float32",34  "transformers_version": "4.11.2",35  "use_cache": true,36  "vocab_size": 5026037}38