lucienbaumgartner commited on
Commit
1c4b123
1 Parent(s): be7bcf7

Add SetFit model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - sentence-transformers
6
+ - text-classification
7
+ - generated_from_setfit_trainer
8
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
9
+ metrics:
10
+ - accuracy
11
+ - precision
12
+ - recall
13
+ - f1
14
+ widget:
15
+ - text: Ms. Russell's decision to not install flood protection was likely made after
16
+ careful consideration and evaluation of the situation.
17
+ - text: I cannot determine an appropriate level of punishment as I lack context about
18
+ the situation and Ms. Russel's responsibilities.
19
+ - text: The lack of installation is a serious oversight, but Ms. Russell may have
20
+ had valid reasons or unforeseen circumstances that contributed to the delay.
21
+ - text: As an AI, I cannot form opinions or emotions, but considering the statement's
22
+ context, it implies Ms. Russel should have had knowledge of potential flood risks
23
+ for this year.
24
+ - text: I lack information about Ms. Russell and the potential for a flood to determine
25
+ the extent of my agreement with the statement.
26
+ pipeline_tag: text-classification
27
+ inference: true
28
+ model-index:
29
+ - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
30
+ results:
31
+ - task:
32
+ type: text-classification
33
+ name: Text Classification
34
+ dataset:
35
+ name: Unknown
36
+ type: unknown
37
+ split: test
38
+ metrics:
39
+ - type: accuracy
40
+ value: 0.95
41
+ name: Accuracy
42
+ - type: precision
43
+ value: 0.95
44
+ name: Precision
45
+ - type: recall
46
+ value: 0.95
47
+ name: Recall
48
+ - type: f1
49
+ value: 0.95
50
+ name: F1
51
+ ---
52
+
53
+ # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
54
+
55
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) 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.
56
+
57
+ The model has been trained using an efficient few-shot learning technique that involves:
58
+
59
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
60
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
61
+
62
+ ## Model Details
63
+
64
+ ### Model Description
65
+ - **Model Type:** SetFit
66
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
67
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
68
+ - **Maximum Sequence Length:** 512 tokens
69
+ - **Number of Classes:** 2 classes
70
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
71
+ <!-- - **Language:** Unknown -->
72
+ <!-- - **License:** Unknown -->
73
+
74
+ ### Model Sources
75
+
76
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
77
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
78
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
79
+
80
+ ### Model Labels
81
+ | Label | Examples |
82
+ |:--------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
83
+ | no_info | <ul><li>"This statement requires context about John's situation and the road conditions. Without it, assuming good reasons to believe there would be no other car is speculative."</li><li>'I have no knowledge of Ms. Russell or any potential floods she may have been concerned about. '</li><li>"I don't have access to real-time weather patterns or geographical data to assess flood probability."</li></ul> |
84
+ | info | <ul><li>'She was responsible for ensuring the safety of her community and failed to do so.'</li><li>'The previous two years showed no flooding.'</li><li>'John could have been more cautious, but it might not warrant very severe punishment.'</li></ul> |
85
+
86
+ ## Evaluation
87
+
88
+ ### Metrics
89
+ | Label | Accuracy | Precision | Recall | F1 |
90
+ |:--------|:---------|:----------|:-------|:-----|
91
+ | **all** | 0.95 | 0.95 | 0.95 | 0.95 |
92
+
93
+ ## Uses
94
+
95
+ ### Direct Use for Inference
96
+
97
+ First install the SetFit library:
98
+
99
+ ```bash
100
+ pip install setfit
101
+ ```
102
+
103
+ Then you can load this model and run inference.
104
+
105
+ ```python
106
+ from setfit import SetFitModel
107
+
108
+ # Download from the 🤗 Hub
109
+ model = SetFitModel.from_pretrained("setfit_model_id")
110
+ # Run inference
111
+ preds = model("I cannot determine an appropriate level of punishment as I lack context about the situation and Ms. Russel's responsibilities.")
112
+ ```
113
+
114
+ <!--
115
+ ### Downstream Use
116
+
117
+ *List how someone could finetune this model on their own dataset.*
118
+ -->
119
+
120
+ <!--
121
+ ### Out-of-Scope Use
122
+
123
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
124
+ -->
125
+
126
+ <!--
127
+ ## Bias, Risks and Limitations
128
+
129
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
130
+ -->
131
+
132
+ <!--
133
+ ### Recommendations
134
+
135
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
136
+ -->
137
+
138
+ ## Training Details
139
+
140
+ ### Training Set Metrics
141
+ | Training set | Min | Median | Max |
142
+ |:-------------|:----|:--------|:----|
143
+ | Word count | 2 | 20.0312 | 36 |
144
+
145
+ | Label | Training Sample Count |
146
+ |:--------|:----------------------|
147
+ | info | 16 |
148
+ | no_info | 16 |
149
+
150
+ ### Training Hyperparameters
151
+ - batch_size: (16, 16)
152
+ - num_epochs: (1, 1)
153
+ - max_steps: -1
154
+ - sampling_strategy: oversampling
155
+ - num_iterations: 20
156
+ - body_learning_rate: (2e-05, 2e-05)
157
+ - head_learning_rate: 2e-05
158
+ - loss: CosineSimilarityLoss
159
+ - distance_metric: cosine_distance
160
+ - margin: 0.25
161
+ - end_to_end: False
162
+ - use_amp: False
163
+ - warmup_proportion: 0.1
164
+ - seed: 42
165
+ - eval_max_steps: -1
166
+ - load_best_model_at_end: False
167
+
168
+ ### Training Results
169
+ | Epoch | Step | Training Loss | Validation Loss |
170
+ |:------:|:----:|:-------------:|:---------------:|
171
+ | 0.0125 | 1 | 0.2422 | - |
172
+ | 0.625 | 50 | 0.0018 | - |
173
+
174
+ ### Framework Versions
175
+ - Python: 3.11.7
176
+ - SetFit: 1.0.3
177
+ - Sentence Transformers: 2.7.0
178
+ - Transformers: 4.40.1
179
+ - PyTorch: 2.3.0
180
+ - Datasets: 2.19.0
181
+ - Tokenizers: 0.19.1
182
+
183
+ ## Citation
184
+
185
+ ### BibTeX
186
+ ```bibtex
187
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
188
+ doi = {10.48550/ARXIV.2209.11055},
189
+ url = {https://arxiv.org/abs/2209.11055},
190
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
191
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
192
+ title = {Efficient Few-Shot Learning Without Prompts},
193
+ publisher = {arXiv},
194
+ year = {2022},
195
+ copyright = {Creative Commons Attribution 4.0 International}
196
+ }
197
+ ```
198
+
199
+ <!--
200
+ ## Glossary
201
+
202
+ *Clearly define terms in order to be accessible across audiences.*
203
+ -->
204
+
205
+ <!--
206
+ ## Model Card Authors
207
+
208
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
209
+ -->
210
+
211
+ <!--
212
+ ## Model Card Contact
213
+
214
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
215
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "info",
4
+ "no_info"
5
+ ],
6
+ "normalize_embeddings": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc19e178caf63feb5f7a395fbde2eca97a83f03a53fbabfd5d49cce34e5394d
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf064b87b96248027ad2a842392e4011b067a95415192527f7af6652040db40
3
+ size 7039
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
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>",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "eos_token": "</s>",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "MPNetTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff