oopere commited on
Commit
1831f5e
·
verified ·
1 Parent(s): f96089c

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +2 -1
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
- size 19989343
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json CHANGED
@@ -10,6 +10,7 @@
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
  "is_local": false,
 
13
  "model_max_length": 262144,
14
  "model_specific_special_tokens": {
15
  "audio_bos_token": "<|audio_start|>",
@@ -23,7 +24,7 @@
23
  "pad_token": "<|endoftext|>",
24
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
  "split_special_tokens": false,
26
- "tokenizer_class": "TokenizersBackend",
27
  "unk_token": null,
28
  "video_token": "<|video_pad|>",
29
  "vision_bos_token": "<|vision_start|>",
 
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
  "is_local": false,
13
+ "local_files_only": false,
14
  "model_max_length": 262144,
15
  "model_specific_special_tokens": {
16
  "audio_bos_token": "<|audio_start|>",
 
24
  "pad_token": "<|endoftext|>",
25
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
  "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
  "unk_token": null,
29
  "video_token": "<|video_pad|>",
30
  "vision_bos_token": "<|vision_start|>",