config.json

{
  "activation_function": "gelu_new",
  "add_cross_attention": false,
  "architectures": [
    "CaelisNeuralBase"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 2,
  "dtype": "float32",
  "embd_pdrop": 0.1,
  "eos_token_id": null,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "cnb3",
  "n_ctx": 1024,
  "n_embd": 1536,
  "n_head": 24,
  "n_inner": null,
  "n_layer": 32,
  "n_positions": 1024,
  "pad_token_id": null,
  "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,
  "tie_word_embeddings": true,
  "transformers_version": "5.17.0",
  "use_cache": true,
  "vocab_size": 50257
}