config.json

{
  "architectures": [
    "Lfm2vlForConditionalGeneration"
  ],
  "boa_token_id": 256000,
  "boi_token": "<start_of_image>",
  "boi_token_id": 64401,
  "bos_token_id": 1,
  "eoa_token_id": 262272,
  "eoi_token": "<end_of_image>",
  "eoi_token_id": 64402,
  "eos_token_id": 7,
  "image_token": "<image_soft_token>",
  "image_token_id": 64400,
  "initializer_range": 0.02,
  "model_type": "lfm2mvl",
  "pad_token_id": 0,
  "text_config": {
    "architectures": [
      "Lfm2ForCausalLM"
    ],
    "block_auto_adjust_ff_dim": true,
    "block_dim": 2048,
    "block_ff_dim": 12288,
    "block_ffn_dim_multiplier": 1.0,
    "block_mlp_init_scale": 1.0,
    "block_multiple_of": 256,
    "block_norm_eps": 1e-05,
    "block_out_init_scale": 1.0,
    "block_use_swiglu": true,
    "block_use_xavier_init": true,
    "bos_token_id": 2,
    "conv_L_cache": 3,
    "conv_bias": false,
    "conv_dim": 2048,
    "conv_dim_out": 2048,
    "conv_use_xavier_init": true,
    "eos_token_id": 1,
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "layer_types": [
      "conv",
      "conv",
      "full_attention",
      "conv",
      "conv",
      "full_attention",
      "conv",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv",
      "full_attention",
      "conv"
    ],
    "max_position_embeddings": 128000,
    "model_type": "lfm2",
    "norm_eps": 1e-05,
    "num_attention_heads": 32,
    "num_heads": 32,
    "num_hidden_layers": 16,
    "num_key_value_heads": 8,
    "rope_theta": 1000000.0,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "use_pos_enc": true,
    "vocab_size": 64403
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0",
  "use_cache": true,
  "vision_config": {
    "architecture": "mobilenetv5_300m_enc",
    "do_pooling": false,
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "label_names": [
      "LABEL_0",
      "LABEL_1"
    ],
    "model_args": null,
    "model_type": "lfm2_vision",
    "num_classes": 2,
    "rms_norm_eps": 1e-06,
    "torch_dtype": "bfloat16",
    "vocab_offset": 262144,
    "vocab_size": 128
  },
  "vision_soft_tokens_per_image": 256,
  "vocab_size": 64403
}