MarkusWesterwald
commited on
Commit
•
9451b5f
1
Parent(s):
4bd497b
Add SetFit model
Browse files- config.json +1 -1
- model_head.pkl +2 -2
- pytorch_model.bin +2 -2
- special_tokens_map.json +7 -0
- tokenizer_config.json +14 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/root/.cache/torch/sentence_transformers/
|
3 |
"architectures": [
|
4 |
"MPNetModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/MarkusWesterwald_topic-level-1-setfit-model/",
|
3 |
"architectures": [
|
4 |
"MPNetModel"
|
5 |
],
|
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 sha256:97eb741b56998a1987be7db9377564ccfd9cfb404cd9c1e3aedf7807949aa808
|
3 |
+
size 156943
|
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:d925a959b9b683989b3a46022dab853ada6d9beed29b85f158ee001517b7a62c
|
3 |
+
size 438012518
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,11 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>",
|
4 |
+
"<pad>",
|
5 |
+
"</s>",
|
6 |
+
"[UNK]",
|
7 |
+
"<mask>"
|
8 |
+
],
|
9 |
"bos_token": "<s>",
|
10 |
"cls_token": "<s>",
|
11 |
"eos_token": "</s>",
|
tokenizer_config.json
CHANGED
@@ -41,7 +41,13 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
@@ -49,12 +55,19 @@
|
|
49 |
"do_lower_case": true,
|
50 |
"eos_token": "</s>",
|
51 |
"mask_token": "<mask>",
|
|
|
52 |
"model_max_length": 512,
|
53 |
"never_split": null,
|
|
|
54 |
"pad_token": "<pad>",
|
|
|
|
|
55 |
"sep_token": "</s>",
|
|
|
56 |
"strip_accents": null,
|
57 |
"tokenize_chinese_chars": true,
|
58 |
"tokenizer_class": "MPNetTokenizer",
|
|
|
|
|
59 |
"unk_token": "[UNK]"
|
60 |
}
|
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
+
"additional_special_tokens": [
|
45 |
+
"<s>",
|
46 |
+
"<pad>",
|
47 |
+
"</s>",
|
48 |
+
"[UNK]",
|
49 |
+
"<mask>"
|
50 |
+
],
|
51 |
"bos_token": "<s>",
|
52 |
"clean_up_tokenization_spaces": true,
|
53 |
"cls_token": "<s>",
|
|
|
55 |
"do_lower_case": true,
|
56 |
"eos_token": "</s>",
|
57 |
"mask_token": "<mask>",
|
58 |
+
"max_length": 512,
|
59 |
"model_max_length": 512,
|
60 |
"never_split": null,
|
61 |
+
"pad_to_multiple_of": null,
|
62 |
"pad_token": "<pad>",
|
63 |
+
"pad_token_type_id": 0,
|
64 |
+
"padding_side": "right",
|
65 |
"sep_token": "</s>",
|
66 |
+
"stride": 0,
|
67 |
"strip_accents": null,
|
68 |
"tokenize_chinese_chars": true,
|
69 |
"tokenizer_class": "MPNetTokenizer",
|
70 |
+
"truncation_side": "right",
|
71 |
+
"truncation_strategy": "longest_first",
|
72 |
"unk_token": "[UNK]"
|
73 |
}
|