{
  "_attn_implementation_autoset": false,
  "add_cross_attention": false,
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "cross_attention_hidden_size": null,
  "decoder_start_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128009,
  "finetuning_task": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "is_decoder": false,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 128009,
  "prefix": null,
  "pretraining_tp": 1,
  "pruned_heads": {},
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_theta": 500000,
    "rope_type": "llama3"
  },
  "sep_token_id": null,
  "task_specific_params": null,
  "tf_legacy_loss": false,
  "tie_encoder_decoder": false,
  "tie_word_embeddings": false,
  "tokenizer_class": null,
  "torchscript": false,
  "transformers_version": "5.7.0",
  "use_bfloat16": false,
  "use_cache": false,
  "vocab_size": 128256
}