embeddinggemma-300m-CoreAI / model /tokenizer /tokenizer_config.json
Ben Graville
embeddinggemma-300m Core AI fp32 static (seq 256), rebuilt on Linux box 2026-08-17; producer coreai-core 1.0.0b2; tokenizer bit-identical to mlboydaisuke@d9a60a18, main.mlirb +262 B (conversion is not byte-deterministic)
2bee70c verified
Raw
History Blame Contribute Delete
705 Bytes
{
"backend": "tokenizers",
"boi_token": "<start_of_image>",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eoi_token": "<end_of_image>",
"eos_token": "<eos>",
"image_token": "<image_soft_token>",
"is_local": false,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 2048,
"model_specific_special_tokens": {
"boi_token": "<start_of_image>",
"eoi_token": "<end_of_image>",
"image_token": "<image_soft_token>"
},
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": null,
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}