Upload 7 files
Browse files- special_tokens_map.json +5 -0
- spiece.model +3 -0
- spiece.vocab +0 -0
- token_fraction.csv +0 -0
- token_fraction_describe.txt +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"mask_token": "…",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cacaa8ed75d01b57939573eb7812b15fa6d98d22d7214c8a29e32e6f90652c41
|
| 3 |
+
size 95279
|
spiece.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
token_fraction.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
token_fraction_describe.txt
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
token text token/text
|
| 2 |
+
count 55681.000000 55681.000000 55681.000000
|
| 3 |
+
mean 53.031824 113.674467 0.474277
|
| 4 |
+
std 44.040030 96.405552 0.091615
|
| 5 |
+
min 7.000000 41.000000 0.144928
|
| 6 |
+
10% 21.000000 47.000000 0.386617
|
| 7 |
+
25% 27.000000 58.000000 0.419355
|
| 8 |
+
33% 31.000000 65.000000 0.431818
|
| 9 |
+
50% 39.000000 82.000000 0.456522
|
| 10 |
+
67% 51.000000 107.000000 0.486339
|
| 11 |
+
75% 61.000000 127.000000 0.506329
|
| 12 |
+
80% 69.000000 147.000000 0.522727
|
| 13 |
+
90% 101.000000 220.000000 0.580000
|
| 14 |
+
95% 138.000000 303.000000 0.652632
|
| 15 |
+
99% 232.000000 510.000000 0.817391
|
| 16 |
+
max 1097.000000 2522.000000 1.411765
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "</s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"4448": {
|
| 20 |
+
"content": "…",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"6000": {
|
| 28 |
+
"content": "<0x{i:02X}>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"clean_up_tokenization_spaces": true,
|
| 37 |
+
"eos_token": "</s>",
|
| 38 |
+
"mask_token": "…",
|
| 39 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 41 |
+
"unk_token": "<unk>"
|
| 42 |
+
}
|