Mistral tokenizer_config.json fix
#1
by
TheBloke
- opened
- tokenizer_config.json +6 -8
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 +37,7 @@
|
|
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/ae9d75c6b4eb39515def78c685fb4d71d49fc2cf/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 |
"trust_remote_code": false,
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": true,
|
|
|
43 |
}
|