config.json

{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_token_index": 32000,
  "model_type": "llava_next",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "LeroyDyer/_Spydaz_Web_AI_LlavaNext",
    "architectures": [
      "MistralForCausalLM"
    ],
    "head_dim": 128,
    "intermediate_size": 14336,
    "max_position_embeddings": 524288,
    "model_type": "mistral",
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 75000000.0,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "unsloth_version": "2024.8"
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.44.2",
  "vision_config": {
    "dropout": 0.0,
    "hidden_size": 768,
    "image_size": 224,
    "intermediate_size": 3072,
    "model_type": "clip_vision_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "patch_size": 32,
    "projection_dim": 512
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}