config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128009,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 24,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pad_token_id": 128263,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "use_cache": false,
  "vocab_size": 156960,
  "quantization_config": {
    "load_in_4bit": true,
    "load_in_8bit": false,
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_use_double_quant": true
  }
}