{
  "architectures": [
    "Ministral3ForCausalLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": null,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 131072,
  "hidden_size": 5120,
  "intermediate_size": 32768,
  "num_hidden_layers": 40,
  "num_attention_heads": 32,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "hidden_act": "silu",
  "max_position_embeddings": 393216,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-05,
  "use_cache": true,
  "pad_token_id": 11,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "tie_word_embeddings": false,
  "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,
  "attention_dropout": 0.0,
  "_name_or_path": "",
  "model_type": "ministral3",
  "output_attentions": false,
  "quantization_config": {
    "quant_method": "glq",
    "codebook": "e8_shell",
    "codesz": 8,
    "bpw": 4
  }
}