config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "dtype": "bfloat16",
  "eos_token_id": [
    1,
    130073
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 4608,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "pad_token_id": 1,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "modules_to_not_convert": null,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 5000000,
    "rope_type": "default"
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.9.0",
  "use_cache": false,
  "vocab_size": 130560
}