Upload tokenizer
Browse files- merges.txt +1 -1
- tokenizer.json +1 -0
- tokenizer_config.json +50 -0
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
à °
|
| 3 |
Ġ Ã
|
| 4 |
Ġ s
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
à °
|
| 3 |
Ġ Ã
|
| 4 |
Ġ s
|
tokenizer.json
CHANGED
|
@@ -84,6 +84,7 @@
|
|
| 84 |
"continuing_subword_prefix": null,
|
| 85 |
"end_of_word_suffix": null,
|
| 86 |
"fuse_unk": false,
|
|
|
|
| 87 |
"vocab": {
|
| 88 |
"<s>": 0,
|
| 89 |
"<pad>": 1,
|
|
|
|
| 84 |
"continuing_subword_prefix": null,
|
| 85 |
"end_of_word_suffix": null,
|
| 86 |
"fuse_unk": false,
|
| 87 |
+
"byte_fallback": false,
|
| 88 |
"vocab": {
|
| 89 |
"<s>": 0,
|
| 90 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,55 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"51000": {
|
| 45 |
+
"content": "<|endoftext|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
"bos_token": "<|endoftext|>",
|
| 54 |
"clean_up_tokenization_spaces": true,
|
| 55 |
"eos_token": "<|endoftext|>",
|