Commit
•
196add0
1
Parent(s):
a8b8545
Upload tokenizer
Browse files- merges.txt +1 -1
- tokenizer.json +1 -0
- tokenizer_config.json +1 -2
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
a n
|
| 3 |
Ġ t
|
| 4 |
i n
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
a n
|
| 3 |
Ġ t
|
| 4 |
i n
|
tokenizer.json
CHANGED
|
@@ -948,6 +948,7 @@
|
|
| 948 |
"continuing_subword_prefix": "",
|
| 949 |
"end_of_word_suffix": "",
|
| 950 |
"fuse_unk": false,
|
|
|
|
| 951 |
"vocab": {
|
| 952 |
"<s>": 0,
|
| 953 |
"<pad>": 1,
|
|
|
|
| 948 |
"continuing_subword_prefix": "",
|
| 949 |
"end_of_word_suffix": "",
|
| 950 |
"fuse_unk": false,
|
| 951 |
+
"byte_fallback": false,
|
| 952 |
"vocab": {
|
| 953 |
"<s>": 0,
|
| 954 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -19,9 +20,7 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
-
"name_or_path": "./out-small-1.1",
|
| 23 |
"pad_token": null,
|
| 24 |
-
"special_tokens_map_file": "./out-small-1.1/special_tokens_map.json",
|
| 25 |
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|