Added the model files
Browse files- config.json +0 -0
- model.safetensors +3 -0
- model_architecture.txt +44 -0
- training_args.bin +3 -0
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6b9160859b4ea1d1a089d69e1d43fd0d00dc0bd4553b3d1e273df320143edf6
|
3 |
+
size 508572928
|
model_architecture.txt
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
RobertaForSequenceClassification(
|
2 |
+
(roberta): RobertaModel(
|
3 |
+
(embeddings): RobertaEmbeddings(
|
4 |
+
(word_embeddings): Embedding(50265, 768, padding_idx=1)
|
5 |
+
(position_embeddings): Embedding(514, 768, padding_idx=1)
|
6 |
+
(token_type_embeddings): Embedding(1, 768)
|
7 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
8 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
9 |
+
)
|
10 |
+
(encoder): RobertaEncoder(
|
11 |
+
(layer): ModuleList(
|
12 |
+
(0-11): 12 x RobertaLayer(
|
13 |
+
(attention): RobertaAttention(
|
14 |
+
(self): RobertaSelfAttention(
|
15 |
+
(query): Linear(in_features=768, out_features=768, bias=True)
|
16 |
+
(key): Linear(in_features=768, out_features=768, bias=True)
|
17 |
+
(value): Linear(in_features=768, out_features=768, bias=True)
|
18 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
19 |
+
)
|
20 |
+
(output): RobertaSelfOutput(
|
21 |
+
(dense): Linear(in_features=768, out_features=768, bias=True)
|
22 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
23 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
24 |
+
)
|
25 |
+
)
|
26 |
+
(intermediate): RobertaIntermediate(
|
27 |
+
(dense): Linear(in_features=768, out_features=3072, bias=True)
|
28 |
+
(intermediate_act_fn): GELUActivation()
|
29 |
+
)
|
30 |
+
(output): RobertaOutput(
|
31 |
+
(dense): Linear(in_features=3072, out_features=768, bias=True)
|
32 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
33 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
34 |
+
)
|
35 |
+
)
|
36 |
+
)
|
37 |
+
)
|
38 |
+
)
|
39 |
+
(classifier): RobertaClassificationHead(
|
40 |
+
(dense): Linear(in_features=768, out_features=768, bias=True)
|
41 |
+
(dropout): Dropout(p=0.1, inplace=False)
|
42 |
+
(out_proj): Linear(in_features=768, out_features=3240, bias=True)
|
43 |
+
)
|
44 |
+
)
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21064e852609f3da1c3a7a0efcf28ba8280c9b08411c9dcf8500bc91e0a261ec
|
3 |
+
size 5112
|