config.json

{
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "dtype": "float32",
  "ignore_index": -100,
  "image_seq_length": 1,
  "image_token_index": 10,
  "model_type": "llava",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.multi_modal_projector.linear_1",
      "model.multi_modal_projector.linear_2",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.1.dev0"
  },
  "text_config": {
    "_attn_implementation_autoset": false,
    "attention_dropout": 0.0,
    "dtype": "float32",
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 262400,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 48,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000000.0,
    "sliding_window": null,
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 131072
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0.dev0",
  "vision_config": {
    "_attn_implementation_autoset": false,
    "attention_dropout": 0.0,
    "dtype": "float32",
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "image_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "pixtral",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 16,
    "rope_theta": 10000.0,
    "tf_legacy_loss": false,
    "use_bfloat16": false
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "full"
}