Update tokenizer (#1)
Browse files- Update tokenizer (abb3db11858e62972d5c98c8dfd0727fdb0d08d9)
- Update README.md (d0dac592adab656aa8928586cf67c8c22879bf5c)
- README.md +1 -1
- special_tokens_map.json +21 -5
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer.model.v3 +0 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
@@ -2,4 +2,4 @@
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
-
The tokenizer for https://huggingface.co/mistralai/
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
+
The tokenizer for https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3.
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
tokenizer.model.v3
ADDED
Binary file (587 kB). View file
|
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|