Upload tokenizer with huggingface_hub
Browse files
tokenizer/tokenizer_config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
|
|
11 |
"do_lower_case": true,
|
12 |
"eos_token": {
|
13 |
"__type": "AddedToken",
|
@@ -19,9 +20,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
-
"name_or_path": "/content/refmdl",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
26 |
"unk_token": {
|
27 |
"__type": "AddedToken",
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
"do_lower_case": true,
|
13 |
"eos_token": {
|
14 |
"__type": "AddedToken",
|
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 77,
|
|
|
23 |
"pad_token": "<|endoftext|>",
|
|
|
24 |
"tokenizer_class": "CLIPTokenizer",
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|