config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "gpt2-medium",
  "activation_function": "gelu_new",
  "architectures": [
    "EryonModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 1024,
  "model_type": "EryonGPT2",
  "n_ctx": 1024,
  "n_embd": 1024,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 24,
  "n_positions": 1024,
  "n_special": 0,
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "pad_token_id": 50256,
  "predict_special_tokens": 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": "4.47.1",
  "use_cache": true,
  "vocab_size": 50257
}