tstadel commited on
Commit
4984ad8
1 Parent(s): eabdfb4

Push model using huggingface_hub.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ metrics:
9
+ - accuracy
10
+ widget: []
11
+ pipeline_tag: text-classification
12
+ inference: true
13
+ base_model: BAAI/bge-base-en-v1.5
14
+ ---
15
+
16
+ # SetFit with BAAI/bge-base-en-v1.5
17
+
18
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
19
+
20
+ The model has been trained using an efficient few-shot learning technique that involves:
21
+
22
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
23
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
24
+
25
+ ## Model Details
26
+
27
+ ### Model Description
28
+ - **Model Type:** SetFit
29
+ - **Sentence Transformer body:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5)
30
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
31
+ - **Maximum Sequence Length:** 512 tokens
32
+ - **Number of Classes:** 2 classes
33
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
34
+ <!-- - **Language:** Unknown -->
35
+ <!-- - **License:** Unknown -->
36
+
37
+ ### Model Sources
38
+
39
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
40
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
41
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
42
+
43
+ ## Uses
44
+
45
+ ### Direct Use for Inference
46
+
47
+ First install the SetFit library:
48
+
49
+ ```bash
50
+ pip install setfit
51
+ ```
52
+
53
+ Then you can load this model and run inference.
54
+
55
+ ```python
56
+ from setfit import SetFitModel
57
+
58
+ # Download from the 🤗 Hub
59
+ model = SetFitModel.from_pretrained("tstadel/answer-classification-setfit-v2-binary")
60
+ # Run inference
61
+ preds = model("I loved the spiderman movie!")
62
+ ```
63
+
64
+ <!--
65
+ ### Downstream Use
66
+
67
+ *List how someone could finetune this model on their own dataset.*
68
+ -->
69
+
70
+ <!--
71
+ ### Out-of-Scope Use
72
+
73
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
74
+ -->
75
+
76
+ <!--
77
+ ## Bias, Risks and Limitations
78
+
79
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
80
+ -->
81
+
82
+ <!--
83
+ ### Recommendations
84
+
85
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
86
+ -->
87
+
88
+ ## Training Details
89
+
90
+ ### Framework Versions
91
+ - Python: 3.8.17
92
+ - SetFit: 1.0.1
93
+ - Sentence Transformers: 2.2.2
94
+ - Transformers: 4.36.2
95
+ - PyTorch: 2.0.1
96
+ - Datasets: 2.13.1
97
+ - Tokenizers: 0.15.0
98
+
99
+ ## Citation
100
+
101
+ ### BibTeX
102
+ ```bibtex
103
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
104
+ doi = {10.48550/ARXIV.2209.11055},
105
+ url = {https://arxiv.org/abs/2209.11055},
106
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
107
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
108
+ title = {Efficient Few-Shot Learning Without Prompts},
109
+ publisher = {arXiv},
110
+ year = {2022},
111
+ copyright = {Creative Commons Attribution 4.0 International}
112
+ }
113
+ ```
114
+
115
+ <!--
116
+ ## Glossary
117
+
118
+ *Clearly define terms in order to be accessible across audiences.*
119
+ -->
120
+
121
+ <!--
122
+ ## Model Card Authors
123
+
124
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
125
+ -->
126
+
127
+ <!--
128
+ ## Model Card Contact
129
+
130
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
131
+ -->
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/setfit_bge-base-en-v1.5_binary/",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-12,
21
+ "max_position_embeddings": 512,
22
+ "model_type": "bert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.2",
4
+ "transformers": "4.28.1",
5
+ "pytorch": "1.13.0+cu117"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "needs_verification",
4
+ "non_verifiable"
5
+ ],
6
+ "normalize_embeddings": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752d8365803ed5e0838404b5972fae6848554b8a1e8d75089d5f3b95a1a03494
3
+ size 437951328
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc438ac9e7d71a242df9f9c31253f75914c6f16e3dfccd8d09613c100b69fa4
3
+ size 6991
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": true
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff