Update tiny models for PersimmonForSequenceClassification

#9
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<unk>": 0,
3
+ "|ENDOFTEXT|": 71013
4
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c884c76ac18bea4703bc13b6a1dedf5a158bd0599aefb0723377ebdee137aa7
3
  size 33620317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91c1f8d52a8f6cc040f483d059d5ffc39b9bab38972d72df35888e5124f7896
3
  size 33620317
special_tokens_map.json CHANGED
@@ -1,16 +1,4 @@
1
  {
2
- "bos_token": {
3
- "content": "|ENDOFTEXT|",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "unk_token": {
10
- "content": "<unk>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- }
16
  }
 
1
  {
2
+ "bos_token": "|ENDOFTEXT|",
3
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
4
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ca9f2afc67c230cfe5513fe038e3538a2f111cccf5c5aac82db24b63fbb884
3
- size 16464024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c624be2d9dddae3e8c82cda48fe5c737ec6710225e953ef851a4023f2d4796a
3
+ size 16464051
tokenizer_config.json CHANGED
@@ -1,29 +1,35 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "|ENDOFTEXT|",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": null,
14
- "legacy": null,
15
  "model_max_length": 512,
16
  "pad_token": null,
17
  "sp_model_kwargs": {},
18
  "spaces_between_special_tokens": false,
19
  "tokenizer_class": "LlamaTokenizer",
20
- "unk_token": {
21
- "__type": "AddedToken",
22
- "content": "<unk>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
  "use_default_system_prompt": true
29
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "71013": {
14
+ "content": "|ENDOFTEXT|",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
  },
22
+ "additional_special_tokens": [],
23
+ "bos_token": "|ENDOFTEXT|",
24
  "clean_up_tokenization_spaces": false,
25
  "eos_token": null,
26
+ "legacy": true,
27
  "model_max_length": 512,
28
  "pad_token": null,
29
  "sp_model_kwargs": {},
30
  "spaces_between_special_tokens": false,
31
  "tokenizer_class": "LlamaTokenizer",
32
+ "tokenizer_file": null,
33
+ "unk_token": "<unk>",
 
 
 
 
 
 
34
  "use_default_system_prompt": true
35
  }