MutazYoune
commited on
Commit
•
858dfad
1
Parent(s):
083c4d1
Upload 5 files
Browse files- config.json +20 -9
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- training_args.bin +2 -2
- vocab.json +0 -0
config.json
CHANGED
@@ -1,25 +1,36 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
|
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 768,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 3072,
|
13 |
-
"layer_norm_eps": 1e-
|
14 |
"max_position_embeddings": 512,
|
15 |
-
"
|
|
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"torch_dtype": "float32",
|
21 |
"transformers_version": "4.26.0.dev0",
|
22 |
-
"type_vocab_size":
|
23 |
-
"
|
24 |
-
"vocab_size": 30522
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
"architectures": [
|
4 |
+
"DebertaV2ForMaskedLM"
|
5 |
],
|
6 |
+
"attention_head_size": 64,
|
7 |
"attention_probs_dropout_prob": 0.1,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 768,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-07,
|
14 |
"max_position_embeddings": 512,
|
15 |
+
"max_relative_positions": -1,
|
16 |
+
"model_type": "deberta-v2",
|
17 |
+
"norm_rel_ebd": "layer_norm",
|
18 |
"num_attention_heads": 12,
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 0,
|
21 |
+
"pooler_dropout": 0,
|
22 |
+
"pooler_hidden_act": "gelu",
|
23 |
+
"pooler_hidden_size": 768,
|
24 |
+
"pos_att_type": [
|
25 |
+
"p2c",
|
26 |
+
"c2p"
|
27 |
+
],
|
28 |
+
"position_biased_input": false,
|
29 |
+
"position_buckets": 256,
|
30 |
+
"relative_attention": true,
|
31 |
+
"share_att_key": true,
|
32 |
"torch_dtype": "float32",
|
33 |
"transformers_version": "4.26.0.dev0",
|
34 |
+
"type_vocab_size": 0,
|
35 |
+
"vocab_size": 128100
|
|
|
36 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
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:ba099290b2e4b3dbebc3b002b1c1ac71a69cf426bdaad3b550f562d84055b2b4
|
3 |
+
size 738280041
|
training_args.bin
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 sha256:61a6741516eacddcb951ae19205fb2c0d32306caf96a02bf85025e3b33b6db83
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|