{
  "attention_dropout": 0.0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 32768,
  "max_position_embeddings": 393216,
  "model_type": "ministral3",
  "num_attention_heads": 32,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 48.0,
    "llama_4_scaling_beta": 0.1,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_theta": 100000000.0,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "sliding_window": null,
  "use_cache": true,
  "vocab_size": 131072,
  "architectures": [
    "Ministral3ForCausalLM"
  ],
  "torch_dtype": "bfloat16",
  "quantization_config": {
    "activation_scheme": "static",
    "dequantize": false,
    "modules_to_not_convert": [
      "lm_head"
    ],
    "quant_method": "fp8",
    "weight_block_size": null
  }
}