isbondarev commited on
Commit
d491d83
·
verified ·
1 Parent(s): 7a6a131

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144,
3
+ "<|im_end|>": 262145
4
+ }
special_tokens_map.json CHANGED
@@ -1,8 +1,14 @@
1
  {
2
  "additional_special_tokens": [
3
- "<start_of_turn>",
4
- "<end_of_turn>"
 
 
 
 
 
5
  ],
 
6
  "bos_token": {
7
  "content": "<bos>",
8
  "lstrip": false,
@@ -10,6 +16,7 @@
10
  "rstrip": false,
11
  "single_word": false
12
  },
 
13
  "eos_token": {
14
  "content": "<eos>",
15
  "lstrip": false,
@@ -17,6 +24,7 @@
17
  "rstrip": false,
18
  "single_word": false
19
  },
 
20
  "pad_token": {
21
  "content": "<pad>",
22
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_end|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
  ],
11
+ "boi_token": "<start_of_image>",
12
  "bos_token": {
13
  "content": "<bos>",
14
  "lstrip": false,
 
16
  "rstrip": false,
17
  "single_word": false
18
  },
19
+ "eoi_token": "<end_of_image>",
20
  "eos_token": {
21
  "content": "<eos>",
22
  "lstrip": false,
 
24
  "rstrip": false,
25
  "single_word": false
26
  },
27
+ "image_token": "<image_soft_token>",
28
  "pad_token": {
29
  "content": "<pad>",
30
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
3
- size 34362873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8d1880ce5dece8db6d91f5fa876d4915eae3adf7044a0e6ed59e7053242463
3
+ size 33384755
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
- size 4241003
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff