Hugging Face's logo

SykoSLM
/
SykoLLM-V5.6

Text Generation
Transformers
Safetensors
Turkish
English
phi3
causal-lm
turkish
llm
pre-training
syko
conversational
text-generation-inference
Model card Files
xet
 Community
SykoSLM commited on
Commit
6b837c5
·
verified ·
1 Parent(s): 20d89be

Upload 2 files

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +60 -0
  2. tokenizer_config.json +48 -5
special_tokens_map.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false,
8
+ "special": true
9
+ },
10
+ "eos_token": {
11
+ "content": "<|endoftext|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false,
16
+ "special": true
17
+ },
18
+ "unk_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false,
24
+ "special": true
25
+ },
26
+ "pad_token": {
27
+ "content": "<|pad|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false,
32
+ "special": true
33
+ },
34
+ "additional_special_tokens": [
35
+ {
36
+ "content": "<|user|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ {
44
+ "content": "<|assistant|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "content": "<|end|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ ]
60
+ }
tokenizer_config.json CHANGED
@@ -1,10 +1,53 @@
1
  {
2
- "backend": "tokenizers",
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
- "is_local": true,
6
- "model_max_length": 1000000000000000019884624838656,
7
  "pad_token": "<|pad|>",
8
- "tokenizer_class": "TokenizersBackend",
9
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  }
 
1
  {
 
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>",
 
5
  "pad_token": "<|pad|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "PreTrainedTokenizerFast",
8
+ "clean_up_tokenization_spaces": false,
9
+ "add_prefix_space": false,
10
+ "added_tokens_decoder": {
11
+ "0": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "1": {
20
+ "content": "<|user|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "2": {
28
+ "content": "<|assistant|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "3": {
36
+ "content": "<|end|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "4": {
44
+ "content": "<|pad|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}<|user|>\n{{ message['content'] }}<|end|>\n{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}<|end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}"
53
  }