config.json

{
  "architectures": [
    "MaincoderForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_maincoder.MaincoderConfig",
    "AutoModel": "modelling_maincoder.MaincoderForCausalLM",
    "AutoModelForCausalLM": "modelling_maincoder.MaincoderForCausalLM"
  },
  "bos_token_id": null,
  "eos_token_id": 151643,
  "head_dim": 96,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "intermediate_size_mlp": 4096,
  "max_position_embeddings": 2048,
  "model_type": "maincoder",
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_qk_norm": true,
  "vocab_size": 151936
}