qducnguyen
commited on
Commit
•
84f9d9a
1
Parent(s):
008efe7
Bump version support
Browse files- .gitattributes +2 -0
- 1_Pooling/config.json +3 -1
- config.json +2 -2
- config_sentence_transformers.json +1 -1
- model.safetensors +3 -0
- tokenizer_config.json +42 -0
.gitattributes
CHANGED
@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
37 |
.git/lfs/objects/cb/fa/cbfae04cc7f3063949a7d81258e185cd31249892768c15e27b70d4797f42b902 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
37 |
.git/lfs/objects/cb/fa/cbfae04cc7f3063949a7d81258e185cd31249892768c15e27b70d4797f42b902 filter=lfs diff=lfs merge=lfs -text
|
38 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
39 |
+
.git/lfs/objects/2d/81/2d8135cb6ff79bf4303fb0afd11808791c9123ae8ee753fccd480207e347963e filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
CHANGED
@@ -3,5 +3,7 @@
|
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
-
"pooling_mode_mean_sqrt_len_tokens": false
|
|
|
|
|
7 |
}
|
|
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false
|
9 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
@@ -21,7 +21,7 @@
|
|
21 |
"position_embedding_type": "absolute",
|
22 |
"tokenizer_class": "PhobertTokenizer",
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 64001
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "output/train_bi-encoder-mnrl-vinai-phobert-base-v2-margin_3.0-2023-08-27_23-13-25/",
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
|
|
21 |
"position_embedding_type": "absolute",
|
22 |
"tokenizer_class": "PhobertTokenizer",
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.38.2",
|
25 |
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 64001
|
config_sentence_transformers.json
CHANGED
@@ -2,6 +2,6 @@
|
|
2 |
"__version__": {
|
3 |
"sentence_transformers": "2.2.2",
|
4 |
"transformers": "4.32.0",
|
5 |
-
"pytorch": "
|
6 |
}
|
7 |
}
|
|
|
2 |
"__version__": {
|
3 |
"sentence_transformers": "2.2.2",
|
4 |
"transformers": "4.32.0",
|
5 |
+
"pytorch": "2.0.0+cu117"
|
6 |
}
|
7 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e681accadaec87e79901db0c3f68e33d996cba334633b6dd0b2483dba4f398e0
|
3 |
+
size 540015464
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,46 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|