config.json

{
  "source_model": "moonshotai/Kimi-K2.5",
  "component": "vision_tower + mm_projector",
  "description": "Vision-only weights extracted from Kimi-K2.5 for use with MLX.",
  "vision_config": {
    "_attn_implementation": "flash_attention_2",
    "init_pos_emb_height": 64,
    "init_pos_emb_time": 4,
    "init_pos_emb_width": 64,
    "merge_kernel_size": [
      2,
      2
    ],
    "merge_type": "sd2_tpool",
    "mm_hidden_size": 1152,
    "mm_projector_type": "patchmerger",
    "patch_size": 14,
    "pos_emb_type": "divided_fixed",
    "projector_hidden_act": "gelu",
    "projector_ln_eps": 1e-05,
    "text_hidden_size": 7168,
    "video_attn_type": "spatial_temporal",
    "vt_hidden_size": 1152,
    "vt_intermediate_size": 4304,
    "vt_num_attention_heads": 16,
    "vt_num_hidden_layers": 27
  },
  "projector": {
    "type": "PatchMergerMLP",
    "input_dim": 4608,
    "hidden_dim": 4608,
    "output_dim": 7168,
    "pre_norm_eps": 1e-05
  },
  "num_tensors": 335,
  "original_dtype": "bfloat16",
  "media_placeholder_token_id": 163605
}