{
  "architectures": [
    "Olmo2NoQKNormPrenormForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "dtype": "float32",
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 4096,
  "model_type": "olmo2_noqknorm_prenorm",
  "num_attention_heads": 16,
  "num_hidden_layers": 16,
  "num_key_value_heads": 16,
  "pad_token_id": 100277,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "vocab_size": 100352,
  "auto_map": {
    "AutoConfig": "configuration_olmo2_noqknorm_prenorm.Olmo2NoQKNormPrenormConfig",
    "AutoModelForCausalLM": "modeling_olmo2_noqknorm_prenorm.Olmo2NoQKNormPrenormForCausalLM"
  }
}