ClaudiaIoana550
commited on
Commit
•
972ab63
1
Parent(s):
3b48d04
Upload tokenizer
Browse files- special_tokens_map.json +2 -1
- tokenizer.json +0 -0
- tokenizer_config.json +2 -3
special_tokens_map.json
CHANGED
@@ -12,5 +12,6 @@
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
-
"eos_token": "<|endoftext|>"
|
|
|
16 |
}
|
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"pad_token": "<|endoftext|>"
|
17 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,12 +1,11 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
"model_input_names": [
|
5 |
"input_ids",
|
6 |
"attention_mask"
|
7 |
],
|
8 |
"model_max_length": 2048,
|
9 |
-
"name_or_path": "tiiuae/falcon_tokenizer",
|
10 |
-
"special_tokens_map_file": null,
|
11 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
12 |
-
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
"eos_token": "<|endoftext|>",
|
5 |
"model_input_names": [
|
6 |
"input_ids",
|
7 |
"attention_mask"
|
8 |
],
|
9 |
"model_max_length": 2048,
|
|
|
|
|
10 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
11 |
+
}
|