Upload tokenizer
Browse files- README.md +4 -4
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +45 -0
README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
datasets:
|
| 3 |
-
- DEplain/DEplain-APA-sent
|
| 4 |
language:
|
| 5 |
- de
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- sari
|
| 8 |
- bleu
|
| 9 |
- bertscore
|
| 10 |
-
library_name: transformers
|
| 11 |
-
base_model: google/mT5-base
|
| 12 |
pipeline_tag: text2text-generation
|
| 13 |
---
|
| 14 |
# Model Card for mT5-base-trimmed_deplain-apa
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- de
|
| 4 |
+
library_name: transformers
|
| 5 |
+
base_model: google/mT5-base
|
| 6 |
+
datasets:
|
| 7 |
+
- DEplain/DEplain-APA-sent
|
| 8 |
metrics:
|
| 9 |
- sari
|
| 10 |
- bleu
|
| 11 |
- bertscore
|
|
|
|
|
|
|
| 12 |
pipeline_tag: text2text-generation
|
| 13 |
---
|
| 14 |
# Model Card for mT5-base-trimmed_deplain-apa
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "</s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41ab3136bdd01e682fc72db7e893d0590fe3ea92eb70afaf98cda162e9507af1
|
| 3 |
+
size 727176
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"max_length": 128,
|
| 34 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_to_multiple_of": null,
|
| 36 |
+
"pad_token": "<pad>",
|
| 37 |
+
"pad_token_type_id": 0,
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"stride": 0,
|
| 41 |
+
"tokenizer_class": "T5Tokenizer",
|
| 42 |
+
"truncation_side": "right",
|
| 43 |
+
"truncation_strategy": "longest_first",
|
| 44 |
+
"unk_token": "<unk>"
|
| 45 |
+
}
|