text_encoder/config.json

{
  "architectures": [
    "Mistral3ForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "image_token_index": 10,
  "model_type": "mistral3",
  "multimodal_projector_bias": false,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "add_skip_keys": false,
    "dequantize_fp32": false,
    "group_size": 0,
    "is_integer": true,
    "is_training": false,
    "modules_dtype_dict": {},
    "modules_to_not_convert": [
      ".img_out",
      "wte",
      "patch_emb",
      ".final_layer",
      "multi_modal_projector",
      "time_text_embed",
      ".emb_in",
      ".img_in",
      ".condition_embedder",
      "lm_head.weight",
      "lm_head",
      ".emb_out",
      "patch_embed",
      ".txt_in",
      ".time_embed",
      ".context_embedder",
      ".x_embedder",
      ".vid_in",
      ".txt_out",
      ".norm_out",
      ".vid_out",
      ".proj_out",
      "patch_embedding"
    ],
    "non_blocking": false,
    "quant_conv": false,
    "quant_method": "sdnq",
    "quantization_device": null,
    "quantized_matmul_dtype": null,
    "return_device": null,
    "svd_rank": 32,
    "svd_steps": 8,
    "use_grad_ckpt": true,
    "use_quantized_matmul": false,
    "use_quantized_matmul_conv": false,
    "use_static_quantization": true,
    "use_stochastic_rounding": false,
    "use_svd": true,
    "weights_dtype": "uint4"
  },
  "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_theta": 1000000000.0,
    "sliding_window": null,
    "use_cache": true,
    "vocab_size": 131072
  },
  "transformers_version": "4.57.1",
  "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_theta": 10000.0
  },
  "vision_feature_layer": -1
}