bossiara13/J.A.R.V.I.S-rust
1
1
Fork 0
Code Issues Pull requests Projects Releases 6 Packages Activity Actions

New intent classification engine - MiniLM L6v2 and MiniLM L12v2 ONNX

Browse source
This commit is contained in:
Priler 2026-02-08 07:16:03 +05:00
parent 4815c7f9bb
commit 8e830334e8
25 changed files with 61932 additions and 150 deletions
Download patch file Download diff file Expand all files Collapse all files

64
resources/models/all-MiniLM-L6-v2/tokenizer_config.json Normal file
View file

@ -0,0 +1,64 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 512,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}