| "{\n\"activation_function\": \"gelu_new\",\n \"architectures\": [\n \"GPT2LMHeadModel\"\n ],\n \"attn_pdrop\": 0.1,\n \"bos_token_id\": 50256,\n \"embd_pdrop\": 0.1,\n \"eos_token_id\": 50256,\n \"initializer_range\": 0.02,\n \"layer_norm_epsilon\": 1e-05,\n \"model_type\": \"gpt2\",\n \"n_ctx\": 1024,\n \"n_embd\": 768,\n \"n_head\": 12,\n \"n_layer\": 12,\n \"n_positions\": 1024,\n \"resid_pdrop\": 0.1,\n \"summary_activation\": null,\n \"summary_first_dropout\": 0.1,\n \"summary_proj_to_labels\": true,\n \"summary_type\": \"cls_index\",\n \"summary_use_proj\": true,\n \"task_specific_params\": {\n \"text-generation\": {\n \"do_sample\": true,\n \"max_length\": 50\n }\n },\n \"vocab_size\": 50257\n}" |