{
  "activation_function": "gelu_new",
  "architectures": [
    "GPTNeoForConditionalCausalLM"
  ],
  "attention_dropout": 0,
  "attention_layers": [
    "global",
    "local",
    "global",
    "local"
  ],
  "attention_types": [
    [
      [
        "global",
        "local"
      ],
      2
    ]
  ],
  "bos_token_id": 50256,
  "classifier_dropout": 0.1,
  "dtype": "float32",
  "embed_dropout": 0,
  "encoder_config": {
    "_name_or_path": "answerdotai/ModernBERT-base",
    "add_cross_attention": false,
    "architectures": [
      "ModernBertForMaskedLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 50281,
    "chunk_size_feed_forward": 0,
    "classifier_activation": "gelu",
    "classifier_bias": false,
    "classifier_dropout": 0.0,
    "classifier_pooling": "mean",
    "cls_token_id": 50281,
    "cross_attention_hidden_size": null,
    "decoder_bias": true,
    "decoder_start_token_id": null,
    "deterministic_flash_attn": false,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dtype": "float32",
    "early_stopping": false,
    "embedding_dropout": 0.0,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50282,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "global_attn_every_n_layers": 3,
    "global_rope_theta": 160000.0,
    "gradient_checkpointing": false,
    "hidden_activation": "gelu",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_cutoff_factor": 2.0,
    "initializer_range": 0.02,
    "intermediate_size": 1152,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "local_attention": 128,
    "local_rope_theta": 10000.0,
    "max_length": 20,
    "max_position_embeddings": 8192,
    "min_length": 0,
    "mlp_bias": false,
    "mlp_dropout": 0.0,
    "model_type": "modernbert",
    "no_repeat_ngram_size": 0,
    "norm_bias": false,
    "norm_eps": 1e-05,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 22,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 50283,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repad_logits_with_grad": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": 50282,
    "sparse_pred_ignore_index": -100,
    "sparse_prediction": false,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 50368
  },
  "eos_token_id": 50256,
  "gradient_checkpointing": false,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neo",
  "num_heads": 16,
  "num_layers": 4,
  "pad_token_id": 50256,
  "resid_dropout": 0,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 50257,
  "window_size": 256
}