Commit
·
bf7c19d
1
Parent(s):
c1d31ef
Upload tokenizer
Browse files- added_tokens.json +41 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +12 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"": 67028,
|
| 3 |
+
"EtOH": 67030,
|
| 4 |
+
"[0]": 67037,
|
| 5 |
+
"[1]": 67065,
|
| 6 |
+
"[TAB][TAB]min": 67038,
|
| 7 |
+
"[TAB][TAB]minimal": 67031,
|
| 8 |
+
"[TAB]if": 67056,
|
| 9 |
+
"[TAB]optimized": 67032,
|
| 10 |
+
"[TAB]portions": 67064,
|
| 11 |
+
"[TAB]tmp": 67042,
|
| 12 |
+
"[[": 67060,
|
| 13 |
+
"[[reactor": 67054,
|
| 14 |
+
"[]": 67052,
|
| 15 |
+
"append": 67062,
|
| 16 |
+
"components": 67036,
|
| 17 |
+
"components]": 67035,
|
| 18 |
+
"compounds": 67048,
|
| 19 |
+
"described": 67034,
|
| 20 |
+
"desired": 67050,
|
| 21 |
+
"elements": 67043,
|
| 22 |
+
"exact": 67058,
|
| 23 |
+
"grams": 67046,
|
| 24 |
+
"have[0]": 67039,
|
| 25 |
+
"inf": 67047,
|
| 26 |
+
"mL": 67033,
|
| 27 |
+
"minimal": 67053,
|
| 28 |
+
"molar": 67044,
|
| 29 |
+
"need": 67045,
|
| 30 |
+
"needed": 67061,
|
| 31 |
+
"needed[1]": 67049,
|
| 32 |
+
"needed]": 67059,
|
| 33 |
+
"optimized": 67055,
|
| 34 |
+
"pcp": 67029,
|
| 35 |
+
"portion": 67051,
|
| 36 |
+
"portions": 67041,
|
| 37 |
+
"reactors": 67066,
|
| 38 |
+
"threshold": 67040,
|
| 39 |
+
"tmp": 67063,
|
| 40 |
+
"zip": 67057
|
| 41 |
+
}
|
source.spm
ADDED
|
Binary file (790 kB). View file
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
target.spm
ADDED
|
Binary file (814 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"model_max_length": 512,
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"separate_vocabs": false,
|
| 7 |
+
"source_lang": "en",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"target_lang": "nl",
|
| 10 |
+
"tokenizer_class": "MarianTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|