{
  "_name_or_path": "Harshad018/distilgpt2-finetuned-wikitext2",
  "_num_labels": 1,
  "activation_function": "gelu_new",
  "architectures": [
    "BertForMaskedLM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "classifier_dropout": null,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0
  },
  "layer_norm_eps": 1e-12,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "n_ctx": 1024,
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 6,
  "n_positions": 1024,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "position_embedding_type": "absolute",
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "type_vocab_size": 2,
  "use_cache": true,
  "vocab_size": 50257
}