{
  "_name_or_path": "gpt2",
  "activation_function": "gelu_new",
  "architectures": [
    "TransformerWithHeads"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 1024,
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 12,
  "n_positions": 1024,
  "output_heads": [
    {
      "block_gradients": false,
      "hidden_size": 0,
      "ignore_pads": true,
      "in_size": 768,
      "is_causal_lm": false,
      "is_regression": false,
      "layer_hook": -1,
      "loss_fct": "cross_entropy",
      "loss_weight": 1.0,
      "name": "imdb_head_1",
      "num_layers": 1,
      "num_outputs": 4,
      "output_activation": "linear",
      "output_bias": false,
      "pred_for_sequence": true,
      "target": "imdb_head_1",
      "trainable": true
    },
    {
      "block_gradients": false,
      "hidden_size": 0,
      "ignore_pads": true,
      "in_size": 768,
      "is_causal_lm": false,
      "is_regression": false,
      "layer_hook": -3,
      "loss_fct": "cross_entropy",
      "loss_weight": 1.0,
      "name": "imdb_head_3",
      "num_layers": 1,
      "num_outputs": 4,
      "output_activation": "linear",
      "output_bias": false,
      "pred_for_sequence": true,
      "target": "imdb_head_3",
      "trainable": true
    },
    {
      "block_gradients": false,
      "hidden_size": 0,
      "ignore_pads": true,
      "in_size": 768,
      "is_causal_lm": false,
      "is_regression": false,
      "layer_hook": -5,
      "loss_fct": "cross_entropy",
      "loss_weight": 1.0,
      "name": "imdb_head_5",
      "num_layers": 1,
      "num_outputs": 4,
      "output_activation": "linear",
      "output_bias": false,
      "pred_for_sequence": true,
      "target": "imdb_head_5",
      "trainable": true
    },
    {
      "block_gradients": false,
      "hidden_size": 0,
      "ignore_pads": true,
      "in_size": 768,
      "is_causal_lm": false,
      "is_regression": false,
      "layer_hook": -7,
      "loss_fct": "cross_entropy",
      "loss_weight": 1.0,
      "name": "imdb_head_7",
      "num_layers": 1,
      "num_outputs": 4,
      "output_activation": "linear",
      "output_bias": false,
      "pred_for_sequence": true,
      "target": "imdb_head_7",
      "trainable": true
    }
  ],
  "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": "4.44.2",
  "use_cache": true,
  "vocab_size": 50257
}