Hugging Face's logo

alexkueck
/
li-tis-tuned-2

Question Answering
Transformers
PyTorch
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
alexkueck commited on
Commit
bf2bda7
路
1 Parent(s): 4121835

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +3 -22
  2. tokenizer_config.json +8 -8
special_tokens_map.json CHANGED
@@ -1,24 +1,5 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
tokenizer_config.json CHANGED
@@ -1,30 +1,30 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": true,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
- "content": "<s>",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
- "content": "</s>",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
19
  "single_word": false
20
  },
 
21
  "model_max_length": 2048,
22
  "pad_token": null,
23
- "sp_model_kwargs": {},
24
- "tokenizer_class": "LlamaTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
27
- "content": "<unk>",
28
  "lstrip": false,
29
  "normalized": true,
30
  "rstrip": false,
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": 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": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "errors": "replace",
22
  "model_max_length": 2048,
23
  "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
 
25
  "unk_token": {
26
  "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
  "lstrip": false,
29
  "normalized": true,
30
  "rstrip": false,