config.json

{
  "_attn_implementation_autoset": true,
  "architectures": [
    "MobileOForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "diffusion_name_or_path": "Efficient-Large-Model/Sana_600M_512px_diffusers",
  "eos_token_id": 151645,
  "freeze_mm_mlp_adapter": false,
  "gen_pooling": "early_pool2d_4",
  "hidden_act": "silu",
  "hidden_size": 896,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "is_train": false,
  "max_position_embeddings": 32768,
  "max_window_layers": 24,
  "mm_hidden_size": 3072,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "mobileclip_l_1024",
  "model_type": "mobile_o_inference",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 512,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "tune_mm_mlp_adapter": false,
  "unfreeze_mm_vision_tower": true,
  "use_cache": true,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vlm_num_layers": 4,
  "vocab_size": 151649
}