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:af96d1e3ec35f6f06c359e12fc6a89e9eb7d60f0c280be0d6af17e6e5d8c544b
|
| 3 |
+
size 98857
|
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 8363.000000 8363.000000 8363.000000
|
| 3 |
+
mean 122.032644 219.241779 0.558474
|
| 4 |
+
std 83.566746 147.172197 0.086161
|
| 5 |
+
min 12.000000 41.000000 0.266667
|
| 6 |
+
10% 37.000000 68.000000 0.455137
|
| 7 |
+
25% 61.000000 112.000000 0.499573
|
| 8 |
+
33% 74.000000 134.000000 0.517241
|
| 9 |
+
50% 103.000000 185.000000 0.553719
|
| 10 |
+
67% 138.000000 248.000000 0.590262
|
| 11 |
+
75% 159.000000 286.000000 0.610390
|
| 12 |
+
80% 176.000000 318.000000 0.626723
|
| 13 |
+
90% 231.000000 410.800000 0.666667
|
| 14 |
+
95% 283.900000 499.900000 0.707317
|
| 15 |
+
99% 401.000000 721.520000 0.800000
|
| 16 |
+
max 664.000000 1179.000000 1.000000
|
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 |
+
"6000": {
|
| 20 |
+
"content": "<0x{i:02X}>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"6001": {
|
| 28 |
+
"content": "…",
|
| 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 |
+
}
|