config.json

{
    "vit_hidden_dim": 768,
    "vit_inter_dim": 3072,
    "vit_patch_size": 16,
    "vit_img_size": 512,
    "vit_n_heads": 12,
    "vit_dropout": 0.0,
    "vit_n_blocks": 12,
    "vit_ln_eps": 1e-06,
    "vit_cls_flag": false,
    "vit_model_type": "google/siglip2-base-patch16-512",
    "lm_hidden_dim": 960,
    "lm_inter_dim": 2560,
    "lm_rms_eps": 1e-05,
    "lm_re_base": 100000,
    "lm_max_position_embeddings": 8192,
    "lm_base_vocab_size": 49152,
    "extra_token_amount": 17,
    "lm_vocab_size": 49169,
    "lm_n_heads": 15,
    "lm_n_kv_heads": 5,
    "lm_dropout": 0.0,
    "lm_n_blocks": 32,
    "lm_attn_scaling": 1.0,
    "lm_max_length": 1024,
    "lm_use_tokens": false,
    "lm_tie_weights": true,
    "lm_model_type": "HuggingFaceTB/SmolLM2-360M-Instruct",
    "lm_tokenizer": "HuggingFaceTB/SmolLM2-360M-Instruct",
    "lm_chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
    "mp_pixel_shuffle_factor": 4,
    "mp_image_token_length": 64,
    "max_img_size": 1024,
    "vlm_extra_tokens": {
        "image_token": "<|image|>",
        "r1c1": "<row_1_col_1>",
        "r1c2": "<row_1_col_2>",
        "r1c3": "<row_1_col_3>",
        "r1c4": "<row_1_col_4>",
        "r2c1": "<row_2_col_1>",
        "r2c2": "<row_2_col_2>",
        "r2c3": "<row_2_col_3>",
        "r2c4": "<row_2_col_4>",
        "r3c1": "<row_3_col_1>",
        "r3c2": "<row_3_col_2>",
        "r3c3": "<row_3_col_3>",
        "r3c4": "<row_3_col_4>",
        "r4c1": "<row_4_col_1>",
        "r4c2": "<row_4_col_2>",
        "r4c3": "<row_4_col_3>",
        "r4c4": "<row_4_col_4>"
    },
    "vlm_load_backbone_weights": true,
    "vlm_checkpoint_path": "checkpoints",
    "hf_repo_name": "nanoVLM"
}