text_encoder/config.json

{
  "architectures": [
    "Mistral3ForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_token_index": 10,
  "model_type": "mistral3",
  "multimodal_projector_bias": false,
  "projector_hidden_act": "gelu",
  "spatial_merge_size": 2,
  "text_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "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_parameters": {
      "rope_theta": 1000000000.0,
      "rope_type": "default"
    },
    "rope_theta": 1000000000.0,
    "sliding_window": null,
    "use_cache": true,
    "vocab_size": 131072
  },
  "transformers_version": "5.0.0.dev0",
  "quantization_config": {
   "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 2,
        "optimize": true,
        "round_zero": true,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "format": "hqq_2bit_packed",
    "skip_modules": [
      "lm_head"
    ]
  },
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "head_dim": 64,
    "hidden_act": "silu",
    "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_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    },
    "rope_theta": 10000.0
  },
  "vision_feature_layer": -1
}