config.json

{
  "architectures": [
    "MllamaForCausalLM"
  ],
  "bos_token_id": 128000,
  "cross_attention_layers": [
    3,
    8,
    13,
    18,
    23,
    28,
    33,
    38
  ],
  "dropout": 0,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "model_type": "mllama_text_model",
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "pad_token_id": 128004,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "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": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}