Commit
·
6133120
1
Parent(s):
e0609f8
Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "\n",
|
3 |
+
"pad_token": "\n",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "\n",
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"name_or_path": "/glusterfs/dfs-gfs-dist/hallepat/ngme",
|
5 |
+
"pad_token": "\n",
|
6 |
+
"special_tokens_map_file": "/glusterfs/dfs-gfs-dist/hallepat/ngme/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "NGMETokenizer",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|