now with correct tavbert model
Browse files- config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./training_5labs/tavbert-tashkeela-pretraining/checkpoint-21098/",
|
3 |
"architectures": [
|
4 |
+
"TaatikModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7641ddd572433f25139514654fcb1a55ba33d467f5d6185a7d6c393f3a9dc5
|
3 |
+
size 349857228
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": {
|
5 |
"strategy": "BatchLongest",
|
6 |
"direction": "Right",
|
|
|
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": "BatchLongest",
|
11 |
"direction": "Right",
|
tokenizer_config.json
CHANGED
@@ -44,7 +44,7 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"mask_token": "[MASK]",
|
47 |
-
"model_max_length":
|
48 |
"pad_token": "[PAD]",
|
49 |
"sep_token": "[SEP]",
|
50 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"mask_token": "[MASK]",
|
47 |
+
"model_max_length": 512,
|
48 |
"pad_token": "[PAD]",
|
49 |
"sep_token": "[SEP]",
|
50 |
"tokenizer_class": "PreTrainedTokenizerFast",
|