Upload 3 files
Browse files- special_tokens_map.json +2 -14
- tokenizer.json +2 -9
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -1,17 +1,5 @@
|
|
1 |
{
|
2 |
-
"eos_token":
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
"pad_token": "<|endoftext|>",
|
10 |
-
"unk_token":
|
11 |
-
"content": "<|endoftext|>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": true,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"pad_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
tokenizer.json
CHANGED
@@ -1,14 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
-
"padding":
|
5 |
-
"strategy": "BatchLongest",
|
6 |
-
"direction": "Left",
|
7 |
-
"pad_to_multiple_of": null,
|
8 |
-
"pad_id": 31989,
|
9 |
-
"pad_type_id": 0,
|
10 |
-
"pad_token": "<|endoftext|>"
|
11 |
-
},
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 31989,
|
@@ -17,7 +10,7 @@
|
|
17 |
"lstrip": false,
|
18 |
"rstrip": false,
|
19 |
"normalized": true,
|
20 |
-
"special":
|
21 |
},
|
22 |
{
|
23 |
"id": 31990,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 31989,
|
|
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
"normalized": true,
|
13 |
+
"special": false
|
14 |
},
|
15 |
{
|
16 |
"id": 31990,
|
tokenizer_config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
-
"special":
|
12 |
},
|
13 |
"31990": {
|
14 |
"content": "<|im_start|>",
|
|
|
8 |
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
+
"special": false
|
12 |
},
|
13 |
"31990": {
|
14 |
"content": "<|im_start|>",
|