config.json

{
  "architectures": [
    "KawnIdefics3ForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      364,
      364
    ],
    [
      364,
      728
    ],
    [
      364,
      1092
    ],
    [
      1092,
      364
    ],
    [
      728,
      364
    ],
    [
      728,
      728
    ],
    [
      728,
      1092
    ],
    [
      1092,
      728
    ],
    [
      1092,
      1092
    ],
    [
      364,
      1456
    ],
    [
      1456,
      364
    ],
    [
      728,
      1456
    ],
    [
      1456,
      728
    ]
  ],
  "image_seq_len": 169,
  "image_seq_length": 169,
  "image_token_id": 58002,
  "model_type": "kawn_idefics3",
  "scale_factor": 2,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "Hennara/kuwain.T8.v7",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "head_dim": 64,
    "hidden_size": 2048,
    "intermediate_size": 5632,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "llama",
    "num_hidden_layers": 30,
    "num_key_value_heads": 4,
    "pad_token_id": null,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "use_cache": false,
    "vocab_size": 58000
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0.dev0",
  "use_cache": true,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "hidden_size": 1152,
    "image_size": 364,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "bfloat16",
    "vision_use_head": false
  },
  "vision_feature_layer": null
}