shadeMe-explosion
commited on
Initial commit
Browse files- config.json +37 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"DebertaV2Model"
|
4 |
+
],
|
5 |
+
"attention_head_size": 8,
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"conv_act": "gelu",
|
8 |
+
"conv_kernel_size": 3,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 32,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 37,
|
14 |
+
"layer_norm_eps": 1e-07,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"max_relative_positions": -1,
|
17 |
+
"model_type": "deberta-v2",
|
18 |
+
"norm_rel_ebd": "layer_norm",
|
19 |
+
"num_attention_heads": 4,
|
20 |
+
"num_hidden_layers": 5,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pooler_dropout": 0,
|
23 |
+
"pooler_hidden_act": "gelu",
|
24 |
+
"pooler_hidden_size": 32,
|
25 |
+
"pos_att_type": [
|
26 |
+
"p2c",
|
27 |
+
"c2p"
|
28 |
+
],
|
29 |
+
"position_biased_input": true,
|
30 |
+
"position_buckets": 64,
|
31 |
+
"relative_attention": true,
|
32 |
+
"share_att_key": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.33.0.dev0",
|
35 |
+
"type_vocab_size": 0,
|
36 |
+
"vocab_size": 1024
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:028fb163a4785eb3467faa3963d217c5264a5a3838faaa4f227d79325e0a67bd
|
3 |
+
size 371548
|