Hugging Face's logo

minpeter
/
tiny-ko-random

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
 Community
minpeter commited on
Commit
d7b9cfb
·
verified ·
1 Parent(s): f381792

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -3
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +9 -9
special_tokens_map.json CHANGED
@@ -2,21 +2,21 @@
2
  "eos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "pad_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
- "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": false,
19
- "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
 
2
  "eos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
+ "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "pad_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": false,
19
+ "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2,29 +2,29 @@
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
  "content": "<|im_start|>",
15
  "lstrip": false,
16
- "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
- "special": true
20
  },
21
- "2": {
22
  "content": "<|im_end|>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
- "special": true
28
  },
29
  "31992": {
30
  "content": "<tool_call>",
@@ -95,7 +95,7 @@
95
  "clean_up_tokenization_spaces": false,
96
  "eos_token": "<|endoftext|>",
97
  "extra_special_tokens": {},
98
- "model_max_length": 2048,
99
  "pad_token": "<|endoftext|>",
100
  "split_special_tokens": false,
101
  "tokenizer_class": "PreTrainedTokenizerFast",
 
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "31989": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "31990": {
14
  "content": "<|im_start|>",
15
  "lstrip": false,
16
+ "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
+ "special": false
20
  },
21
+ "31991": {
22
  "content": "<|im_end|>",
23
  "lstrip": false,
24
+ "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
+ "special": false
28
  },
29
  "31992": {
30
  "content": "<tool_call>",
 
95
  "clean_up_tokenization_spaces": false,
96
  "eos_token": "<|endoftext|>",
97
  "extra_special_tokens": {},
98
+ "model_max_length": 1000000000000000019884624838656,
99
  "pad_token": "<|endoftext|>",
100
  "split_special_tokens": false,
101
  "tokenizer_class": "PreTrainedTokenizerFast",