Hugging Face's logo

webpolis
/
zenos-gpt-j-6B-instruct-4bit

Text Generation
Transformers
PyTorch
Safetensors
gptj
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
webpolis commited on
Commit
e3888e2
•
1 Parent(s): 5e0c2b6

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. special_tokens_map.json +31 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +41 -13
README.md CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  # Zenos GPT-J 6B Instruct 4-bit
2
 
3
  ## Model Overview
 
1
+ ---
2
+ {}
3
+ ---
4
  # Zenos GPT-J 6B Instruct 4-bit
5
 
6
  ## Model Overview
special_tokens_map.json CHANGED
@@ -1,8 +1,35 @@
1
  {
2
  "additional_special_tokens": [
3
- "<|endoftext|>"
 
 
4
  ],
5
- "bos_token": "<|endoftext|>",
6
- "eos_token": "<|endoftext|>",
7
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
  ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,32 @@
1
  {
2
- "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "50257": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  "content": "<|vulgarg|>",
14
  "lstrip": false,
15
  "normalized": true,
@@ -17,7 +34,7 @@
17
  "single_word": false,
18
  "special": false
19
  },
20
- "50258": {
21
  "content": "[INST]",
22
  "lstrip": false,
23
  "normalized": true,
@@ -25,7 +42,7 @@
25
  "single_word": false,
26
  "special": false
27
  },
28
- "50259": {
29
  "content": "[/INST]",
30
  "lstrip": false,
31
  "normalized": true,
@@ -35,12 +52,23 @@
35
  }
36
  },
37
  "additional_special_tokens": [
38
- "<|endoftext|>"
 
 
39
  ],
40
- "bos_token": "<|endoftext|>",
41
- "clean_up_tokenization_spaces": true,
42
- "eos_token": "<|endoftext|>",
43
- "model_max_length": 2048,
44
- "tokenizer_class": "GPT2Tokenizer",
45
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
46
  }
 
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": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
  "content": "<|vulgarg|>",
31
  "lstrip": false,
32
  "normalized": true,
 
34
  "single_word": false,
35
  "special": false
36
  },
37
+ "32001": {
38
  "content": "[INST]",
39
  "lstrip": false,
40
  "normalized": true,
 
42
  "single_word": false,
43
  "special": false
44
  },
45
+ "32002": {
46
  "content": "[/INST]",
47
  "lstrip": false,
48
  "normalized": true,
 
52
  }
53
  },
54
  "additional_special_tokens": [
55
+ "<unk>",
56
+ "<s>",
57
+ "</s>"
58
  ],
59
+ "bos_token": "<s>",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "</s>",
62
+ "legacy": true,
63
+ "max_length": 512,
64
+ "model_max_length": 1000000000000000019884624838656,
65
+ "pad_token": "</s>",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "stride": 0,
69
+ "tokenizer_class": "LlamaTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "<unk>",
73
+ "use_default_system_prompt": true
74
  }