config.json

{
  "_name_or_path": "gpt2",
  "activation_function": "leaky_relu",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_block_resid_gain": 1,
  "attn_block_skip_gain": 1,
  "attn_mat_resid_gain": 1,
  "attn_mat_skip_gain": 0,
  "attn_pdrop": 0,
  "bos_token_id": 0,
  "centre_attn": false,
  "centre_attn_gain": 1.0,
  "embd_pdrop": 0,
  "eos_token_id": 0,
  "first_layer_value_resid_gain": null,
  "initializer_range": 0.02,
  "key_init_std": null,
  "last_layer_proj_resid_gain": null,
  "layer_norm_epsilon": 1e-05,
  "lrelu_neg_slope": 0,
  "mlp_block_resid_gain": 1,
  "mlp_block_skip_gain": 1,
  "mlp_proj_init_std": false,
  "model_type": "gpt2",
  "n_ctx": 128,
  "n_embd": 64,
  "n_head": 2,
  "n_inner": 256,
  "n_layer": 2,
  "n_positions": 1024,
  "norm_position": "pre",
  "norm_type": "rmsnorm",
  "output_attentions": "false",
  "parallel_layers": false,
  "proj_init_type": "normal",
  "proj_resid_gain": 1.0,
  "proj_skip_gain": null,
  "query_init_std": null,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0,
  "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
    }
  },
  "tie_valproj_init": null,
  "torch_dtype": "float32",
  "trainable_attn_block_gains": false,
  "trainable_attn_mat_gains": false,
  "trainable_mlp_block_gains": false,
  "trainable_proj_gains": false,
  "trainable_value_gains": false,
  "transformers_version": "4.38.1",
  "use_cache": true,
  "val_init_type": "normal",
  "val_proj_init_std": null,
  "value_resid_gain": 1,
  "value_skip_gain": 0,
  "vocab_size": 50000
}