kiddothe2b
commited on
Commit
•
c0f8f94
1
Parent(s):
a11ff70
Initial commit V2
Browse files- config.json +78 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"HATForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"encoder_layout": {
|
8 |
+
"0": {
|
9 |
+
"document_encoder": false,
|
10 |
+
"sentence_encoder": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"document_encoder": false,
|
14 |
+
"sentence_encoder": true
|
15 |
+
},
|
16 |
+
"10": {
|
17 |
+
"document_encoder": false,
|
18 |
+
"sentence_encoder": true
|
19 |
+
},
|
20 |
+
"11": {
|
21 |
+
"document_encoder": true,
|
22 |
+
"sentence_encoder": true
|
23 |
+
},
|
24 |
+
"2": {
|
25 |
+
"document_encoder": true,
|
26 |
+
"sentence_encoder": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"document_encoder": false,
|
30 |
+
"sentence_encoder": true
|
31 |
+
},
|
32 |
+
"4": {
|
33 |
+
"document_encoder": false,
|
34 |
+
"sentence_encoder": true
|
35 |
+
},
|
36 |
+
"5": {
|
37 |
+
"document_encoder": true,
|
38 |
+
"sentence_encoder": true
|
39 |
+
},
|
40 |
+
"6": {
|
41 |
+
"document_encoder": false,
|
42 |
+
"sentence_encoder": true
|
43 |
+
},
|
44 |
+
"7": {
|
45 |
+
"document_encoder": false,
|
46 |
+
"sentence_encoder": true
|
47 |
+
},
|
48 |
+
"8": {
|
49 |
+
"document_encoder": true,
|
50 |
+
"sentence_encoder": true
|
51 |
+
},
|
52 |
+
"9": {
|
53 |
+
"document_encoder": false,
|
54 |
+
"sentence_encoder": true
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 3072,
|
62 |
+
"layer_norm_eps": 1e-12,
|
63 |
+
"max_position_embeddings": 128,
|
64 |
+
"max_sentence_length": 128,
|
65 |
+
"max_sentences": 32,
|
66 |
+
"model_max_length": 4096,
|
67 |
+
"model_type": "hat",
|
68 |
+
"num_attention_heads": 12,
|
69 |
+
"num_hidden_layers": 12,
|
70 |
+
"pad_token_id": 1,
|
71 |
+
"position_embedding_type": "absolute",
|
72 |
+
"sentence_split_strategy": "standrad",
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.24.0.dev0",
|
75 |
+
"type_vocab_size": 2,
|
76 |
+
"use_cache": true,
|
77 |
+
"vocab_size": 50265
|
78 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5748e3cb09ececa83c120444068ed85433bf7923749cbda3e432f9ce5249fed
|
3 |
+
size 611243305
|