config.json

{
  "architectures": [
    "MllamaForCausalLM"
  ],
  "bos_token_id": 128000,
  "cross_attention_layers": [
    3,
    8,
    13,
    18,
    23,
    28,
    33,
    38,
    43,
    48,
    53,
    58,
    63,
    68,
    73,
    78,
    83,
    88,
    93,
    98
  ],
  "dropout": 0,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "model_type": "mllama_text_model",
  "num_attention_heads": 64,
  "num_hidden_layers": 100,
  "num_key_value_heads": 8,
  "pad_token_id": 128004,
  "quantization_config": {
    "activation_scheme": "static",
    "ignored_layers": [
      "lm_head"
    ],
    "kv_cache_scheme": "static",
    "quant_method": "fp8"
  },
  "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": "4.45.1",
  "use_cache": true,
  "vocab_size": 128256
}