tokenizer
Browse files- README.md +1 -1
- tokenizer.json +16 -2
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
| 3 |
-
base_model: nlpaueb/legal-bert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
- precision
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-sa-4.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
base_model: nlpaueb/legal-bert-base-uncased
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
- precision
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|