Hugging Face's logo

Thimira
/
sinhala-llama-2-7b-chat-hf

Text Generation
PEFT
PyTorch
TensorBoard
Safetensors
Sinhala
llama
trl
sft
text-generation-inference
Model card Files Metrics Community
Thimira commited on
Commit
642b711
•
1 Parent(s): 5652f6c

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +1 -2
  2. tokenizer_config.json +24 -40
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -143,7 +143,6 @@
143
  "end_of_word_suffix": null,
144
  "fuse_unk": true,
145
  "byte_fallback": true,
146
- "ignore_merges": false,
147
  "vocab": {
148
  "<unk>": 0,
149
  "<s>": 1,
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
143
  "end_of_word_suffix": null,
144
  "fuse_unk": true,
145
  "byte_fallback": true,
 
146
  "vocab": {
147
  "<unk>": 0,
148
  "<s>": 1,
tokenizer_config.json CHANGED
@@ -1,48 +1,32 @@
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
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "32000": {
30
- "content": "<pad>",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- }
37
  },
38
- "bos_token": "<s>",
39
  "clean_up_tokenization_spaces": false,
40
- "eos_token": "</s>",
 
 
 
 
 
 
 
41
  "legacy": false,
42
  "model_max_length": 1000000000000000019884624838656,
43
- "pad_token": "</s>",
44
  "sp_model_kwargs": {},
45
  "tokenizer_class": "LlamaTokenizer",
46
- "unk_token": "<unk>",
47
- "use_default_system_prompt": false
 
 
 
 
 
 
48
  }
 
1
  {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
10
  "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
  }