Commit
•
f9d4363
1
Parent(s):
73c7bc4
Upload tokenizer
Browse files- special_tokens_map.json +4 -28
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -1,26 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "<image>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"content": "<end_of_utterance>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
],
|
| 25 |
"bos_token": {
|
| 26 |
"content": "<s>",
|
|
@@ -36,13 +18,7 @@
|
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
},
|
| 39 |
-
"pad_token":
|
| 40 |
-
"content": "<unk>",
|
| 41 |
-
"lstrip": false,
|
| 42 |
-
"normalized": false,
|
| 43 |
-
"rstrip": false,
|
| 44 |
-
"single_word": false
|
| 45 |
-
},
|
| 46 |
"unk_token": {
|
| 47 |
"content": "<unk>",
|
| 48 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<fake_token_around_image>",
|
| 4 |
+
"<image>",
|
| 5 |
+
"<end_of_utterance>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
|
|
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
+
"pad_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"unk_token": {
|
| 23 |
"content": "<unk>",
|
| 24 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -60,7 +60,7 @@
|
|
| 60 |
"clean_up_tokenization_spaces": false,
|
| 61 |
"eos_token": "</s>",
|
| 62 |
"model_max_length": 1000000000000000019884624838656,
|
| 63 |
-
"pad_token": "
|
| 64 |
"processor_class": "Idefics2Processor",
|
| 65 |
"sp_model_kwargs": {},
|
| 66 |
"spaces_between_special_tokens": false,
|
|
|
|
| 60 |
"clean_up_tokenization_spaces": false,
|
| 61 |
"eos_token": "</s>",
|
| 62 |
"model_max_length": 1000000000000000019884624838656,
|
| 63 |
+
"pad_token": "</s>",
|
| 64 |
"processor_class": "Idefics2Processor",
|
| 65 |
"sp_model_kwargs": {},
|
| 66 |
"spaces_between_special_tokens": false,
|