ApostolosK
commited on
Initial model upload
Browse files- config.json +25 -0
- pytorch.model-230000.bin +3 -0
- sentencepiece.model +3 -0
- tokenizer_config.json +6 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0.1,
|
3 |
+
"hidden_act": "gelu",
|
4 |
+
"hidden_dropout_prob": 0.1,
|
5 |
+
"hidden_size": 768,
|
6 |
+
"initializer_range": 0.02,
|
7 |
+
"intermediate_size": 3072,
|
8 |
+
"max_position_embeddings": 512,
|
9 |
+
"relative_attention": true,
|
10 |
+
"position_buckets": 256,
|
11 |
+
"norm_rel_ebd": "layer_norm",
|
12 |
+
"share_att_key": true,
|
13 |
+
"pos_att_type": "p2c|c2p",
|
14 |
+
"layer_norm_eps": 1e-7,
|
15 |
+
"max_relative_positions": -1,
|
16 |
+
"position_biased_input": false,
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"attention_head_size": 64,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"type_vocab_size": 0,
|
21 |
+
"vocab_size": 50100,
|
22 |
+
"model_type": "deberta-v2",
|
23 |
+
"architectures": ["DebertaV2Model"],
|
24 |
+
"tokenizer_class": "DebertaV2Tokenizer"
|
25 |
+
}
|
pytorch.model-230000.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:188586666f4047ab4e36e7d5bb956e80c7f1d41a9f404ef7dba07d8f37ebb9da
|
3 |
+
size 249956079
|
sentencepiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53943749cee1a32c11d02d56c2cef3420fdc42a572685d2829e1bc95f29f44d6
|
3 |
+
size 1519783
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 512,
|
3 |
+
"padding_side": "right",
|
4 |
+
"truncation_side": "right"
|
5 |
+
}
|
6 |
+
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|