tiny-random-VaultGemmaForCausalLM / tokenizer_config.json
hf-transformers-bot's picture
Update tiny models for VaultGemmaForCausalLM
a87c179 verified
Raw
History Blame Contribute Delete
7.19 kB
{
"backend": "tokenizers",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"extra_special_tokens": [
"<pad>",
"<eos>",
"<bos>",
"<mask>",
"<2mass>",
"[@BOS@]",
"[multimodal]",
"<ctrl1>",
"<ctrl2>",
"<ctrl3>",
"<ctrl4>",
"<ctrl5>",
"<ctrl6>",
"<ctrl7>",
"<ctrl8>",
"<ctrl9>",
"<ctrl10>",
"<ctrl11>",
"<ctrl12>",
"<ctrl13>",
"<ctrl14>",
"<ctrl15>",
"<ctrl16>",
"<ctrl17>",
"<ctrl18>",
"<ctrl19>",
"<ctrl20>",
"<ctrl21>",
"<ctrl22>",
"<ctrl23>",
"<ctrl24>",
"<ctrl25>",
"<ctrl26>",
"<ctrl27>",
"<ctrl28>",
"<ctrl29>",
"<ctrl30>",
"<ctrl31>",
"<ctrl32>",
"<ctrl33>",
"<ctrl34>",
"<ctrl35>",
"<ctrl36>",
"<ctrl37>",
"<ctrl38>",
"<ctrl39>",
"<ctrl40>",
"<ctrl41>",
"<ctrl42>",
"<ctrl43>",
"<ctrl44>",
"<ctrl45>",
"<ctrl46>",
"<ctrl47>",
"<ctrl48>",
"<ctrl49>",
"<ctrl50>",
"<ctrl51>",
"<ctrl52>",
"<ctrl53>",
"<ctrl54>",
"<ctrl55>",
"<ctrl56>",
"<ctrl57>",
"<ctrl58>",
"<ctrl59>",
"<ctrl60>",
"<ctrl61>",
"<ctrl62>",
"<ctrl63>",
"<ctrl64>",
"<ctrl65>",
"<ctrl66>",
"<ctrl67>",
"<ctrl68>",
"<ctrl69>",
"<ctrl70>",
"<ctrl71>",
"<ctrl72>",
"<ctrl73>",
"<ctrl74>",
"<ctrl75>",
"<ctrl76>",
"<ctrl77>",
"<ctrl78>",
"<ctrl79>",
"<ctrl80>",
"<ctrl81>",
"<ctrl82>",
"<ctrl83>",
"<ctrl84>",
"<ctrl85>",
"<ctrl86>",
"<ctrl87>",
"<ctrl88>",
"<ctrl89>",
"<ctrl90>",
"<ctrl91>",
"<ctrl92>",
"<ctrl93>",
"<ctrl94>",
"<ctrl95>",
"<ctrl96>",
"<ctrl97>",
"<ctrl98>",
"<ctrl99>",
"<ctrl100>",
"\n",
"\n\n",
"\n\n\n",
"\n\n\n\n",
"\n\n\n\n\n",
"\n\n\n\n\n\n",
"\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
"▁▁",
"▁▁▁",
"▁▁▁▁",
"▁▁▁▁▁",
"▁▁▁▁▁▁",
"▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
"<table>",
"<caption>",
"<thead>",
"<tbody>",
"<tfoot>",
"<tr>",
"<th>",
"<td>",
"</table>",
"</caption>",
"</thead>",
"</tbody>",
"</tfoot>",
"</tr>",
"</th>",
"</td>",
"<h1>",
"<h2>",
"<h3>",
"<h4>",
"<h5>",
"<h6>",
"<blockquote>",
"</h1>",
"</h2>",
"</h3>",
"</h4>",
"</h5>",
"</h6>",
"</blockquote>",
"<strong>",
"<em>",
"<b>",
"<i>",
"<u>",
"<s>",
"<sub>",
"<sup>",
"<code>",
"</strong>",
"</em>",
"</b>",
"</i>",
"</u>",
"</s>",
"</sub>",
"</sup>",
"</code>",
"[toxicity=0]",
"\t\t",
"\t\t\t",
"\t\t\t\t",
"\t\t\t\t\t",
"\t\t\t\t\t\t",
"\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
"<start_of_image>"
],
"is_local": true,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"vocab_file": "/home/runner/.cache/huggingface/hub/models--google--vaultgemma-1b/snapshots/f9624dafc1760cb2f6039e86e12055d6559d7abb/tokenizer.model"
}