{
  "architectures": [
    "Ministral3ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 12288,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 262144,
  "model_type": "ministral3",
  "num_attention_heads": 96,
  "num_hidden_layers": 88,
  "num_key_value_heads": 8,
  "pad_token_id": 11,
  "quantization_config": {
    "autoround_version": "0.10.1",
    "batch_size": 1,
    "bits": 4,
    "damp_percent": 0.01,
    "data_type": "int",
    "desc_act": false,
    "group_size": 128,
    "iters": 1000,
    "lm_head": false,
    "low_gpu_mem_usage": true,
    "provider": "auto-round",
    "quant_method": "gptq",
    "sym": true,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "beta_fast": 4.0,
    "beta_slow": 1.0,
    "factor": 64.0,
    "llama_4_scaling_beta": 0.0,
    "mscale": 1.0,
    "mscale_all_dim": 0.0,
    "original_max_position_embeddings": 4096,
    "rope_theta": 1000000.0,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "5.3.0",
  "use_cache": true,
  "vocab_size": 131072,
  "torch_dtype": "float16"
}