Commit
•
0c33cd8
1
Parent(s):
4736edc
Upload tokenizer
Browse files- arcade100k.tiktoken +0 -0
- special_tokens_map.json +4 -0
- tokenizer_config.json +15 -0
arcade100k.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<|endoftext|>",
|
| 3 |
+
"pad_token": "<|endoftext|>"
|
| 4 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoTokenizer": [
|
| 5 |
+
"stabilityai/stablelm-2-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
|
| 6 |
+
null
|
| 7 |
+
]
|
| 8 |
+
},
|
| 9 |
+
"clean_up_tokenization_spaces": true,
|
| 10 |
+
"eos_token": "<|endoftext|>",
|
| 11 |
+
"errors": "replace",
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"pad_token": "<|endoftext|>",
|
| 14 |
+
"tokenizer_class": "Arcade100kTokenizer"
|
| 15 |
+
}
|