Hugging Face's logo

kreabs
/
bloom-6b4-clp-german-oasst-v0.1_finetuned_dolly_1600

Text Generation
Transformers
Safetensors
bloom
Inference Endpoints
text-generation-inference
Model card Files Community
kreabs commited on
Commit
19a7606
•
1 Parent(s): 9ad2db1

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +7 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +44 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +68 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 50258,
3
+ "<|prefix_begin|>": 50261,
4
+ "<|prefix_end|>": 50260,
5
+ "<|prompter|>": 50257,
6
+ "<|system|>": 50259
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|prompter|>",
4
+ "<|assistant|>",
5
+ "<|system|>",
6
+ "<|prefix_end|>",
7
+ "<|prefix_begin|>"
8
+ ],
9
+ "bos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|prompter|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|assistant|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|system|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<|prefix_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<|prefix_begin|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "additional_special_tokens": [
54
+ "<|prompter|>",
55
+ "<|assistant|>",
56
+ "<|system|>",
57
+ "<|prefix_end|>",
58
+ "<|prefix_begin|>"
59
+ ],
60
+ "bos_token": "<|endoftext|>",
61
+ "clean_up_tokenization_spaces": true,
62
+ "eos_token": "<|endoftext|>",
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<|endoftext|>",
65
+ "sep_token": "<|endoftext|>",
66
+ "tokenizer_class": "GPT2Tokenizer",
67
+ "unk_token": "<|endoftext|>"
68
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff