Align tokenizer with mistral-common (#6)
Browse files- Align tokenizer with mistral-common (31c929a50f1fd49436077cc67effb5f500013152)
Co-authored-by: Matthew Carrigan <[email protected]>
- README.md +1 -1
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +0 -0
README.md
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- fr
|
| 5 |
- it
|
| 6 |
- de
|
| 7 |
- es
|
| 8 |
- en
|
|
|
|
| 9 |
tags:
|
| 10 |
- moe
|
| 11 |
---
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- fr
|
| 4 |
- it
|
| 5 |
- de
|
| 6 |
- es
|
| 7 |
- en
|
| 8 |
+
license: apache-2.0
|
| 9 |
tags:
|
| 10 |
- moe
|
| 11 |
---
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|