config.json

{
  "_commit_hash": null,
  "architectures": [
    "RewardModel"
  ],
  "base_model_config": {
    "_name_or_path": "EleutherAI/gpt-neo-1.3B",
    "activation_function": "gelu_new",
    "add_cross_attention": false,
    "architectures": [
      "GPTNeoForCausalLM"
    ],
    "attention_dropout": 0,
    "attention_layers": [
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local",
      "global",
      "local"
    ],
    "attention_types": [
      [
        [
          "global",
          "local"
        ],
        12
      ]
    ],
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 50256,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embed_dropout": 0,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50256,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "hidden_size": 2048,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": null,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_epsilon": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 2048,
    "min_length": 0,
    "model_type": "gpt_neo",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 16,
    "num_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "resid_dropout": 0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "suppress_tokens": null,
    "task_specific_params": {
      "text-generation": {
        "do_sample": true,
        "max_length": 50,
        "temperature": 0.9
      }
    },
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": "GPT2Tokenizer",
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.26.1",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50257,
    "window_size": 256
  },
  "model_type": "reward_model",
  "torch_dtype": "float32",
  "transformers_version": null
}