config.json

{
  "activation_function": "gelu_new",
  "adaptation_rate": 0.05,
  "additional_special_tokens": [
    "<greeting>",
    "<farewell>",
    "<thank>",
    "<apology>"
  ],
  "architectures": [
    "GPT2Model"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": -1,
  "contextual_embedding_dim": 2048,
  "device": "cuda",
  "dropout_rate": 0.1,
  "embd_pdrop": 0.1,
  "embedding_dim": 2048,
  "eos_token_id": -1,
  "hidden_dim": 2048,
  "initializer_range": 0.02,
  "innovative_growth_capacity": 50000,
  "integration_settings": {
    "config_name": "config.json",
    "load_from_transformers": true,
    "pytorch_dump_folder_path": "./model_save",
    "pytorch_model_bin_name": "pytorch_model.bin"
  },
  "layer_norm_epsilon": 1e-05,
  "lstm_hidden_dim": 2048,
  "max_memory_size": 100000,
  "max_neurons": 100,
  "meta_learning_rate": 0.001,
  "model_type": "gpt2",
  "n_embd": 768,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 24,
  "n_positions": 2048,
  "num_embeddings": 50268,
  "num_heads": 64,
  "num_layers": 24,
  "output_attentions": true,
  "output_hidden_states": true,
  "pad_token_id": -100,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "sep_token_id": -1,
  "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,
      "length_penalty": 1.0,
      "max_length": 50,
      "no_repeat_ngram_size": 2,
      "repetition_penalty": 1.2,
      "temperature": 0.9,
      "top_k": 50,
      "top_p": 0.95
    }
  },
    "return_dict": true,
    "torchscript": false,
    "torch_dtype": null,
    "use_bfloat16": false,
    "tf_legacy_loss": false,
    "pruned_heads": {},
    "tie_word_embeddings": true,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "finetuning_task": null,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "tokenizer_class": null,
    "prefix": null,
    "decoder_start_token_id": null,
    "problem_type": null,
    "transformers_version": null,
    "vocab_size": 50281,
    "context_window": 20,
    "env": null,
    "state_shape": null,
    "action_size": 50257,
    "q_model": null,
    "target_q_model": null
}