{
  "_name_or_path": "/home/ubuntu/training/falcon-lima/model_output/palmyra-med-20b/checkpoint-2100",
  "activation_function": "gelu",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 50256,
  "embd_pdrop": 0.1,
  "eos_token_id": 50256,
  "initializer_range": 0.008165,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_embd": 6144,
  "n_head": 48,
  "n_inner": 24576,
  "n_layer": 44,
  "n_positions": 2048,
  "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,
  "torch_dtype": "float16",
  "transformers_version": "4.30.0.dev0",
  "use_cache": false,
  "vocab_size": 50259
}