config.json

{
  "_name_or_path": "EleutherAI/gpt-neo-125M",
  "activation_function": "gelu_new",
  "architectures": [
    "Re_gptForCausalLM"
  ],
  "attention_dropout": 0,
  "attention_layers": [
    "global",
    "local",
    "global",
    "local",
    "global",
    "local",
    "global",
    "local",
    "global",
    "local",
    "global",
    "local"
  ],
  "attention_types": [
    [
      [
        "global",
        "local"
      ],
      6
    ]
  ],
  "bos_token_id": 50256,
  "chunk_size": 64,
  "dec_attn_dropout": 0.25,
  "dec_cross_attn_layers": [
    5,
    128
  ],
  "dec_ff_dropout": 0.25,
  "dec_heads": 16,
  "dim_head": 64,
  "embed_dropout": 0,
  "enc_att_dropout": 0.0,
  "enc_cross_attn_layers": null,
  "enc_depth": 2,
  "enc_dim": 768,
  "enc_ff_dropout": 0.0,
  "enc_heads": 16,
  "eos_token_id": 50256,
  "ff_mult": 4,
  "gradient_checkpointing": false,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": null,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "re_gpt",
  "num_heads": 12,
  "num_layers": 12,
  "resid_dropout": 0,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.20.1",
  "use_cache": true,
  "vocab_size": 50257,
  "window_size": 256
}