add tokenizer code

This commit is contained in:
coffee
2025-04-29 18:21:17 +08:00
parent c0bcb8947e
commit d5ebd9df0e
43 changed files with 546364 additions and 21 deletions
@@ -0,0 +1,15 @@
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<pad>",
"sep_token": "</s>",
"unk_token": "<unk>"
}