bsen26 commited on
Commit
37e8957
1 Parent(s): e572516

Add SetFit model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - text: delivery and food preparation was suoer fast. nice
12
+ - text: Hard, stale cookies that were probably sitting out for days.
13
+ - text: I ordered an extra side of guacamole that never arrived with my meal.
14
+ - text: Kulang talaga ang mga sangkap, mukhang hindi kumpleto ang aking order.
15
+ - text: The steak was so overcooked and tough, I couldn't even cut through it with
16
+ a knife.
17
+ pipeline_tag: text-classification
18
+ inference: true
19
+ base_model: meedan/paraphrase-filipino-mpnet-base-v2
20
+ ---
21
+
22
+ # SetFit with meedan/paraphrase-filipino-mpnet-base-v2
23
+
24
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [meedan/paraphrase-filipino-mpnet-base-v2](https://huggingface.co/meedan/paraphrase-filipino-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.
25
+
26
+ The model has been trained using an efficient few-shot learning technique that involves:
27
+
28
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
29
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
30
+
31
+ ## Model Details
32
+
33
+ ### Model Description
34
+ - **Model Type:** SetFit
35
+ - **Sentence Transformer body:** [meedan/paraphrase-filipino-mpnet-base-v2](https://huggingface.co/meedan/paraphrase-filipino-mpnet-base-v2)
36
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
37
+ - **Maximum Sequence Length:** 128 tokens
38
+ - **Number of Classes:** 6 classes
39
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
40
+ <!-- - **Language:** Unknown -->
41
+ <!-- - **License:** Unknown -->
42
+
43
+ ### Model Sources
44
+
45
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
46
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
47
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
48
+
49
+ ### Model Labels
50
+ | Label | Examples |
51
+ |:------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
52
+ | 0 | <ul><li>'I specifically asked for no onions, yet my sandwich was loaded with them when delivered.'</li><li>'The delivery driver spilled half my order all over the bag. What a mess!'</li><li>'Two hour wait only for my pizza to arrive burnt on the bottom from sitting too long.'</li></ul> |
53
+ | 2 | <ul><li>'Found a long strand of hair hanging out of my sealed takeout burger container.'</li><li>'Bits of plastic were baked into the crust of the takeout pizza I received.'</li><li>'The takeout container for my soup was leaking and left a trail of foul-smelling liquid.'</li></ul> |
54
+ | 1 | <ul><li>'Sobrang luto at tigas na para bang kahoy ang aking karne.'</li><li>'Sobrang lata ng pagkaluto, hindi na makain ang aking litsong manok.'</li><li>'Pizza crust was burnt black on the bottom yet still doughy raw on top.'</li></ul> |
55
+ | 3 | <ul><li>'Half the ingredients were missing from my order like they forgot to include them.'</li><li>'Binayaran ko ang dami, pero napakaliit lang ng portion size na naibigay sa akin.'</li><li>'The plate looked full but it was all rice, with small paltry portions of the main items.'</li></ul> |
56
+ | 4 | <ul><li>'Bland, overcooked chicken, soggy vegetables and hard, stale naan bread.'</li><li>'Tiny portion sizes, freezing cold plates, and a hair baked into the bread.'</li><li>'Every single thing I tried to order was met with confusion, attitude and mistakes.'</li></ul> |
57
+ | 5 | <ul><li>'From the appetizer to dessert, everything was prepared flawlessly. 10/10!'</li><li>"The chilaquiles were authentic, flavor-packed and easily the best I've had."</li><li>'You can really taste the freshness of the local ingredients in every bite.'</li></ul> |
58
+
59
+ ## Uses
60
+
61
+ ### Direct Use for Inference
62
+
63
+ First install the SetFit library:
64
+
65
+ ```bash
66
+ pip install setfit
67
+ ```
68
+
69
+ Then you can load this model and run inference.
70
+
71
+ ```python
72
+ from setfit import SetFitModel
73
+
74
+ # Download from the 🤗 Hub
75
+ model = SetFitModel.from_pretrained("bsen26/eyeR-classification-model-1.0")
76
+ # Run inference
77
+ preds = model("delivery and food preparation was suoer fast. nice")
78
+ ```
79
+
80
+ <!--
81
+ ### Downstream Use
82
+
83
+ *List how someone could finetune this model on their own dataset.*
84
+ -->
85
+
86
+ <!--
87
+ ### Out-of-Scope Use
88
+
89
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
90
+ -->
91
+
92
+ <!--
93
+ ## Bias, Risks and Limitations
94
+
95
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
96
+ -->
97
+
98
+ <!--
99
+ ### Recommendations
100
+
101
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
102
+ -->
103
+
104
+ ## Training Details
105
+
106
+ ### Training Set Metrics
107
+ | Training set | Min | Median | Max |
108
+ |:-------------|:----|:--------|:----|
109
+ | Word count | 3 | 12.6833 | 17 |
110
+
111
+ | Label | Training Sample Count |
112
+ |:------|:----------------------|
113
+ | 0 | 20 |
114
+ | 1 | 20 |
115
+ | 2 | 20 |
116
+ | 3 | 20 |
117
+ | 4 | 20 |
118
+ | 5 | 20 |
119
+
120
+ ### Training Hyperparameters
121
+ - batch_size: (16, 16)
122
+ - num_epochs: (1, 1)
123
+ - max_steps: -1
124
+ - sampling_strategy: oversampling
125
+ - num_iterations: 20
126
+ - body_learning_rate: (2e-05, 2e-05)
127
+ - head_learning_rate: 2e-05
128
+ - loss: CosineSimilarityLoss
129
+ - distance_metric: cosine_distance
130
+ - margin: 0.25
131
+ - end_to_end: False
132
+ - use_amp: False
133
+ - warmup_proportion: 0.1
134
+ - seed: 42
135
+ - eval_max_steps: -1
136
+ - load_best_model_at_end: False
137
+
138
+ ### Training Results
139
+ | Epoch | Step | Training Loss | Validation Loss |
140
+ |:------:|:----:|:-------------:|:---------------:|
141
+ | 0.0033 | 1 | 0.2048 | - |
142
+ | 0.1667 | 50 | 0.048 | - |
143
+ | 0.3333 | 100 | 0.0148 | - |
144
+ | 0.5 | 150 | 0.0011 | - |
145
+ | 0.6667 | 200 | 0.0009 | - |
146
+ | 0.8333 | 250 | 0.0005 | - |
147
+ | 1.0 | 300 | 0.0008 | - |
148
+
149
+ ### Framework Versions
150
+ - Python: 3.10.12
151
+ - SetFit: 1.0.3
152
+ - Sentence Transformers: 2.6.1
153
+ - Transformers: 4.38.2
154
+ - PyTorch: 2.2.1+cu121
155
+ - Datasets: 2.18.0
156
+ - Tokenizers: 0.15.2
157
+
158
+ ## Citation
159
+
160
+ ### BibTeX
161
+ ```bibtex
162
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
163
+ doi = {10.48550/ARXIV.2209.11055},
164
+ url = {https://arxiv.org/abs/2209.11055},
165
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
166
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
167
+ title = {Efficient Few-Shot Learning Without Prompts},
168
+ publisher = {arXiv},
169
+ year = {2022},
170
+ copyright = {Creative Commons Attribution 4.0 International}
171
+ }
172
+ ```
173
+
174
+ <!--
175
+ ## Glossary
176
+
177
+ *Clearly define terms in order to be accessible across audiences.*
178
+ -->
179
+
180
+ <!--
181
+ ## Model Card Authors
182
+
183
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
184
+ -->
185
+
186
+ <!--
187
+ ## Model Card Contact
188
+
189
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
190
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meedan/paraphrase-filipino-mpnet-base-v2",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.38.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.2.0",
4
+ "transformers": "4.17.0",
5
+ "pytorch": "1.10.0"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee6910e3578cbabf83f7445e873f187250ba2e0b9569edbfe65cd2429ddf4b5
3
+ size 1112197096
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b76d2a858173093751cf44ec5cec7a85225121e18f1701152283538f6dcec4f
3
+ size 37799
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": 128,
3
+ "do_lower_case": false
4
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa685fc160bbdbab64058d4fc91b60e62d207e8dc60b9af5c002c5ab946ded00
3
+ size 17083009
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "250001": {
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
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }