Fix tokenizer_config.json, add Fast tokenizer from Mistral 7B 0.1 (#1)
Browse files- Fix tokenizer_config.json, add Fast tokenizer from Mistral 7B 0.1 (6e287954f15b86e7e3a71c660afc2252ca076203)
Co-authored-by: Tom Jobbins <[email protected]>
- tokenizer.json +0 -0
- tokenizer_config.json +7 -10
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -4,25 +4,25 @@
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
-
"lstrip":
|
8 |
"normalized": false,
|
9 |
-
"rstrip":
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
-
"lstrip":
|
16 |
"normalized": false,
|
17 |
-
"rstrip":
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
-
"lstrip":
|
24 |
"normalized": false,
|
25 |
-
"rstrip":
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
}
|
@@ -37,9 +37,6 @@
|
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
-
"tokenizer_file": "/home/teknium/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/f966a600a1f2c35a067dcb16b24bbf9ac3b85799/tokenizer.json",
|
41 |
-
"trust_remote_code": false,
|
42 |
"unk_token": "<unk>",
|
43 |
-
"use_default_system_prompt": true
|
44 |
-
"use_fast": true
|
45 |
}
|
|
|
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 |
}
|
|
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
|
|
42 |
}
|