Added the tokenizer by
Browse files- README.md +2 -2
- config.json +38 -24
README.md
CHANGED
@@ -19,7 +19,7 @@ widget:
|
|
19 |
example_title: "Similarity Detection."
|
20 |
---
|
21 |
|
22 |
-
A fine-tuned model based on the **DeBERTaV3** model of Microsoft and fine-tuned on **Glue QQP**, which detects the linguistical similarities between two questions and whether they are
|
23 |
|
24 |
## Model Hyperparameters
|
25 |
|
@@ -64,4 +64,4 @@ booktitle={International Conference on Learning Representations},
|
|
64 |
year={2021},
|
65 |
url={https://openreview.net/forum?id=XPZIaotutsD}
|
66 |
}
|
67 |
-
```
|
|
|
19 |
example_title: "Similarity Detection."
|
20 |
---
|
21 |
|
22 |
+
A fine-tuned model based on the **DeBERTaV3** model of Microsoft and fine-tuned on **Glue QQP**, which detects the linguistical similarities between two questions and whether they are duplicates questions or different.
|
23 |
|
24 |
## Model Hyperparameters
|
25 |
|
|
|
64 |
year={2021},
|
65 |
url={https://openreview.net/forum?id=XPZIaotutsD}
|
66 |
}
|
67 |
+
```
|
config.json
CHANGED
@@ -1,25 +1,39 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"attention_probs_dropout_prob": 0.1,
|
4 |
+
"hidden_act": "gelu",
|
5 |
+
"hidden_dropout_prob": 0.1,
|
6 |
+
"hidden_size": 768,
|
7 |
+
"id2label": {
|
8 |
+
"0": "Different",
|
9 |
+
"1": "Duplicate"
|
10 |
+
},
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"label2id": {
|
14 |
+
"Different": 0,
|
15 |
+
"Duplicate": 1
|
16 |
+
},
|
17 |
+
"layer_norm_eps": 1e-07,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"max_relative_positions": -1,
|
20 |
+
"model_type": "deberta-v2",
|
21 |
+
"norm_rel_ebd": "layer_norm",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"pooler_dropout": 0,
|
26 |
+
"pooler_hidden_act": "gelu",
|
27 |
+
"pooler_hidden_size": 768,
|
28 |
+
"pos_att_type": [
|
29 |
+
"p2c",
|
30 |
+
"c2p"
|
31 |
+
],
|
32 |
+
"position_biased_input": false,
|
33 |
+
"position_buckets": 256,
|
34 |
+
"relative_attention": true,
|
35 |
+
"share_att_key": true,
|
36 |
+
"transformers_version": "4.24.0",
|
37 |
+
"type_vocab_size": 0,
|
38 |
+
"vocab_size": 128100
|
39 |
+
}
|