ColModernVBERT-CoreAI / query /tokenizer /tokenizer_config.json
mlboydaisuke's picture
ColModernVBERT -> Core AI: query + doc encoders (fp16/fp32), visual document retrieval (late-interaction / MaxSim)
2175916 verified
Raw
History Blame Contribute Delete
792 Bytes
{
"backend": "tokenizers",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"extra_special_tokens": [
"<fake_token_around_image>",
"<image>",
"<end_of_utterance>"
],
"is_local": false,
"legacy": false,
"local_files_only": false,
"mask_token": "[MASK]",
"max_length": 8192,
"model_input_names": [
"input_ids",
"attention_mask",
"pixel_values",
"pixel_attention_mask"
],
"model_max_length": 8192,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "left",
"processor_class": "ColModernVBertProcessor",
"sep_token": "[SEP]",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}