{
  "architectures": [
    "NeuronLMForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_neuron_lm.NeuronLMConfig",
    "AutoModelForCausalLM": "modeling_neuron_lm.NeuronLMForCausalLM"
  },
  "bos_token_id": 0,
  "dtype": "bfloat16",
  "eos_token_id": 5,
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "is_causal": true,
  "is_decoder": true,
  "max_position_embeddings": 4096,
  "model_type": "neuron_lm",
  "num_attention_heads": 28,
  "num_hidden_layers": 36,
  "num_key_value_heads": 4,
  "pad_token_id": 3,
  "residual_dropout": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 500000.0,
    "rope_type": "default"
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.12.1",
  "use_cache": false,
  "use_qk_norm": true,
  "vocab_size": 48000
}