ritheshSree
commited on
Commit
·
ebdefbf
1
Parent(s):
a8ebdba
Add SetFit model
Browse files- config.json +23 -14
- model_head.pkl +2 -2
- pytorch_model.bin +2 -2
- sentence_bert_config.json +1 -1
- special_tokens_map.json +6 -6
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -55
config.json
CHANGED
@@ -1,24 +1,33 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0
|
7 |
-
"bos_token_id":
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
|
|
11 |
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
|
|
13 |
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-
|
15 |
-
"max_position_embeddings":
|
16 |
-
"model_type": "
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
|
|
|
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.20.1",
|
23 |
-
"
|
|
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-albert-small-v2/",
|
3 |
"architectures": [
|
4 |
+
"AlbertModel"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
"hidden_size": 768,
|
16 |
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
"intermediate_size": 3072,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "albert",
|
22 |
+
"net_structure_type": 0,
|
23 |
"num_attention_heads": 12,
|
24 |
+
"num_hidden_groups": 1,
|
25 |
+
"num_hidden_layers": 6,
|
26 |
+
"num_memory_blocks": 0,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.20.1",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"vocab_size": 30000
|
33 |
}
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad0d0fcb3b1639c34c09f65f1398227ad23e3329fbd7238d22772bc1018cf2f4
|
3 |
+
size 7042
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6af13288ade3ac4bea6e2ff81ca89df51253baa5c2f51e4c9e46dc3a6c92445c
|
3 |
+
size 46746519
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 100,
|
3 |
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"bos_token": "
|
3 |
-
"cls_token": "
|
4 |
-
"eos_token": "
|
5 |
"mask_token": {
|
6 |
-
"content": "
|
7 |
"lstrip": true,
|
8 |
"normalized": false,
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
"pad_token": "<pad>",
|
13 |
-
"sep_token": "
|
14 |
-
"unk_token": "
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
"lstrip": true,
|
8 |
"normalized": false,
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
"pad_token": "<pad>",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
3 |
+
size 760289
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,67 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
"cls_token": {
|
11 |
-
"__type": "AddedToken",
|
12 |
-
"content": "<s>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": true,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false
|
17 |
-
},
|
18 |
-
"do_basic_tokenize": true,
|
19 |
"do_lower_case": true,
|
20 |
-
"eos_token":
|
21 |
-
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": true,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
},
|
28 |
"mask_token": {
|
29 |
"__type": "AddedToken",
|
30 |
-
"content": "
|
31 |
"lstrip": true,
|
32 |
"normalized": true,
|
33 |
"rstrip": false,
|
34 |
"single_word": false
|
35 |
},
|
36 |
"model_max_length": 512,
|
37 |
-
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-
|
38 |
-
"
|
39 |
-
"
|
40 |
-
|
41 |
-
"content": "<pad>",
|
42 |
-
"lstrip": false,
|
43 |
-
"normalized": true,
|
44 |
-
"rstrip": false,
|
45 |
-
"single_word": false
|
46 |
-
},
|
47 |
-
"sep_token": {
|
48 |
-
"__type": "AddedToken",
|
49 |
-
"content": "</s>",
|
50 |
-
"lstrip": false,
|
51 |
-
"normalized": true,
|
52 |
-
"rstrip": false,
|
53 |
-
"single_word": false
|
54 |
-
},
|
55 |
"special_tokens_map_file": null,
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"tokenizer_class": "MPNetTokenizer",
|
59 |
-
"unk_token": {
|
60 |
-
"__type": "AddedToken",
|
61 |
-
"content": "[UNK]",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": true,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false
|
66 |
-
}
|
67 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"do_lower_case": true,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"mask_token": {
|
8 |
"__type": "AddedToken",
|
9 |
+
"content": "[MASK]",
|
10 |
"lstrip": true,
|
11 |
"normalized": true,
|
12 |
"rstrip": false,
|
13 |
"single_word": false
|
14 |
},
|
15 |
"model_max_length": 512,
|
16 |
+
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-albert-small-v2/",
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"remove_space": true,
|
19 |
+
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"special_tokens_map_file": null,
|
21 |
+
"tokenizer_class": "AlbertTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|