config.json

{
  "_attn_implementation_autoset": true,
  "architectures": [
    "Mistral3ForConditionalGeneration"
  ],
  "image_token_index": 10,
  "model_type": "mistral3",
  "multimodal_projector_bias": false,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "ignore": [
      "language_model.lm_head",
      "re:vision_tower.*",
      "re:multi_modal_projector.*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "spatial_merge_size": 2,
  "text_config": {
    "attention_dropout": 0.0,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 32768,
    "max_position_embeddings": 131072,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000000.0,
    "sliding_window": null,
    "use_cache": true,
    "vocab_size": 131072
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.50.0.dev0",
  "vision_config": {
    "attention_dropout": 0.0,
    "head_dim": 64,
    "hidden_act": "gelu",
    "hidden_size": 1024,
    "image_size": 1540,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "pixtral",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "rope_theta": 10000.0
  },
  "vision_feature_layer": -1
}