{
  "architectures": [
    "Lfm2VlForConditionalGeneration"
  ],
  "do_image_splitting": false,
  "downsample_factor": 2,
  "dtype": "bfloat16",
  "encoder_patch_size": 16,
  "image_token_id": 32000,
  "max_image_tokens": 64,
  "max_pixels_tolerance": 2.0,
  "max_tiles": 1,
  "min_image_tokens": 32,
  "min_tiles": 1,
  "model_type": "lfm2_vl",
  "projector_bias": true,
  "projector_hidden_act": "gelu",
  "projector_hidden_size": 2048,
  "projector_use_layernorm": false,
  "text_config": {
    "_name_or_path": "oddadmix/50M-2048-Emhotob",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "dtype": "bfloat16",
    "eos_token_id": 2,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 512,
    "initializer_range": 0.02,
    "intermediate_size": 1408,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 8,
    "num_hidden_layers": 12,
    "num_key_value_heads": 4,
    "pad_token_id": 1,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 10000,
      "rope_type": "default"
    },
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 32064
  },
  "tie_word_embeddings": true,
  "tile_size": 512,
  "transformers_version": "5.15.0",
  "use_image_special_tokens": true,
  "use_thumbnail": false,
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip2_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_patches": 256,
    "patch_size": 16,
    "vision_use_head": false
  }
}