config.json

{
  "_name_or_path": "google/paligemma-3b-mix-224",
  "architectures": [
    "PaliGemmaForConditionalGeneration"
  ],
  "bos_token_id": 2,
  "eos_token_id": 1,
  "hidden_size": 2048,
  "ignore_index": -100,
  "image_token_index": 257152,
  "model_type": "paligemma",
  "pad_token_id": 0,
  "projection_dim": 2048,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "text_config": {
    "hidden_size": 2048,
    "intermediate_size": 16384,
    "model_type": "gemma",
    "num_attention_heads": 8,
    "num_hidden_layers": 18,
    "num_image_tokens": 256,
    "num_key_value_heads": 1,
    "torch_dtype": "float32",
    "vocab_size": 257216
  },
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "vision_config": {
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "num_image_tokens": 256,
    "patch_size": 14,
    "projection_dim": 2048,
    "projector_hidden_act": "gelu_fast",
    "vision_use_head": false
  },
  "vocab_size": 257216
}