higgsfield
commited on
Commit
•
4e8ab51
1
Parent(s):
2ed9c4a
Upload tokenizer
Browse files- added_tokens.json +6 -0
- special_tokens_map.json +11 -0
- tokenizer.model +3 -0
- tokenizer_config.json +57 -0
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0,
|
5 |
+
"<|pad|>": 32000
|
6 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "<|pad|>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|pad|>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": true,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"additional_special_tokens": [
|
39 |
+
"<unk>",
|
40 |
+
"<s>",
|
41 |
+
"</s>"
|
42 |
+
],
|
43 |
+
"bos_token": "<s>",
|
44 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
45 |
+
"clean_up_tokenization_spaces": false,
|
46 |
+
"eos_token": "</s>",
|
47 |
+
"legacy": true,
|
48 |
+
"model_max_length": 2048,
|
49 |
+
"pad_token": "<|pad|>",
|
50 |
+
"padding_side": "right",
|
51 |
+
"sp_model_kwargs": {},
|
52 |
+
"spaces_between_special_tokens": false,
|
53 |
+
"tokenizer_class": "LlamaTokenizer",
|
54 |
+
"tokenizer_file": "/home/nonroot/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/5e9c98b96d071dce59368012254c55b0ec6f8658/tokenizer.json",
|
55 |
+
"unk_token": "<unk>",
|
56 |
+
"use_default_system_prompt": true
|
57 |
+
}
|