Hugging Face's logo

ryeyoo
/
sentimentizer-router

Text Classification
setfit
Joblib
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
text-embeddings-inference
Model card Files
xet
 Community
ryeyoo commited on
Commit
8cc4ca2
·
verified ·
1 Parent(s): 19a07cd

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +114 -6
  2. model.safetensors +1 -1
  3. router_config.json +9 -0
  4. router_head.joblib +3 -0
README.md CHANGED
@@ -4,7 +4,14 @@ tags:
4
  - sentence-transformers
5
  - text-classification
6
  - generated_from_setfit_trainer
7
- widget: []
 
 
 
 
 
 
 
8
  metrics:
9
  - accuracy
10
  pipeline_tag: text-classification
@@ -14,7 +21,7 @@ inference: true
14
 
15
  # SetFit
16
 
17
- This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
18
 
19
  The model has been trained using an efficient few-shot learning technique that involves:
20
 
@@ -26,7 +33,7 @@ The model has been trained using an efficient few-shot learning technique that i
26
  ### Model Description
27
  - **Model Type:** SetFit
28
  <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
29
- - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
30
  - **Maximum Sequence Length:** 512 tokens
31
  - **Number of Classes:** 3 classes
32
  <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
@@ -39,6 +46,13 @@ The model has been trained using an efficient few-shot learning technique that i
39
  - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
40
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
41
 
 
 
 
 
 
 
 
42
  ## Uses
43
 
44
  ### Direct Use for Inference
@@ -55,9 +69,9 @@ Then you can load this model and run inference.
55
  from setfit import SetFitModel
56
 
57
  # Download from the 🤗 Hub
58
- model = SetFitModel.from_pretrained("ryeyoo/sentimentizer-router")
59
  # Run inference
60
- preds = model("I loved the spiderman movie!")
61
  ```
62
 
63
  <!--
@@ -86,8 +100,102 @@ preds = model("I loved the spiderman movie!")
86
 
87
  ## Training Details
88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  ### Framework Versions
90
- - Python: 3.12.13
91
  - SetFit: 1.1.3
92
  - Sentence Transformers: 5.5.0
93
  - Transformers: 5.8.1
 
4
  - sentence-transformers
5
  - text-classification
6
  - generated_from_setfit_trainer
7
+ widget:
8
+ - text: I got the wrong food, clearly a mix-up by the server.
9
+ - text: The menu looked great, but the booming music meant we couldn't even discuss
10
+ what to order.
11
+ - text: We were left waiting 45 minutes beyond our booked time.
12
+ - text: The bartender completely understood my celiac needs and made sure my drinks
13
+ were safe, what great service!
14
+ - text: Way too loud to chat comfortably.
15
  metrics:
16
  - accuracy
17
  pipeline_tag: text-classification
 
21
 
22
  # SetFit
23
 
24
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A NoneType instance is used for classification.
25
 
26
  The model has been trained using an efficient few-shot learning technique that involves:
27
 
 
33
  ### Model Description
34
  - **Model Type:** SetFit
35
  <!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
36
+ - **Classification head:** a NoneType instance
37
  - **Maximum Sequence Length:** 512 tokens
38
  - **Number of Classes:** 3 classes
39
  <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 
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
+ | general | <ul><li>"Even with the waiter's glowing recommendation, the pasta was just run-of-the-mill."</li><li>'It was an acceptable plate of pasta, just lacking that wow factor.'</li><li>'There was so much salt on the garlic bread it crunched.'</li></ul> |
53
+ | service | <ul><li>'So impressed by the bartender who remembered my vegan preferences and suggested perfect drinks accordingly.'</li><li>'The pace of the service was outrageously slow for a restaurant with no other guests.'</li><li>'We got the whole meal for free after telling the manager about the unacceptable wait time.'</li></ul> |
54
+ | dietary | <ul><li>'I ordered gluten-free bread and they brought out the regular kind by mistake.'</li><li>'My order went in so fast because the dairy-free options were impossible to miss on the menu.'</li><li>"What really impressed me wasn't just the food, but how clearly they labeled the dairy-free items."</li></ul> |
55
+
56
  ## Uses
57
 
58
  ### Direct Use for Inference
 
69
  from setfit import SetFitModel
70
 
71
  # Download from the 🤗 Hub
72
+ model = SetFitModel.from_pretrained("setfit_model_id")
73
  # Run inference
74
+ preds = model("Way too loud to chat comfortably.")
75
  ```
76
 
77
  <!--
 
100
 
101
  ## Training Details
102
 
103
+ ### Training Set Metrics
104
+ | Training set | Min | Median | Max |
105
+ |:-------------|:----|:--------|:----|
106
+ | Word count | 4 | 12.6582 | 28 |
107
+
108
+ | Label | Training Sample Count |
109
+ |:--------|:----------------------|
110
+ | dietary | 367 |
111
+ | service | 416 |
112
+ | general | 399 |
113
+
114
+ ### Training Hyperparameters
115
+ - batch_size: (16, 16)
116
+ - num_epochs: (1, 1)
117
+ - max_steps: -1
118
+ - sampling_strategy: oversampling
119
+ - num_iterations: 20
120
+ - body_learning_rate: (2e-05, 1e-05)
121
+ - head_learning_rate: 0.01
122
+ - loss: CosineSimilarityLoss
123
+ - distance_metric: cosine_distance
124
+ - margin: 0.25
125
+ - end_to_end: False
126
+ - use_amp: False
127
+ - warmup_proportion: 0.1
128
+ - l2_weight: 0.01
129
+ - seed: 42
130
+ - eval_max_steps: -1
131
+ - load_best_model_at_end: False
132
+
133
+ ### Training Results
134
+ | Epoch | Step | Training Loss | Validation Loss |
135
+ |:------:|:----:|:-------------:|:---------------:|
136
+ | 0.0003 | 1 | 0.2153 | - |
137
+ | 0.0169 | 50 | 0.1885 | - |
138
+ | 0.0338 | 100 | 0.0788 | - |
139
+ | 0.0508 | 150 | 0.0191 | - |
140
+ | 0.0677 | 200 | 0.0100 | - |
141
+ | 0.0846 | 250 | 0.0057 | - |
142
+ | 0.1015 | 300 | 0.0033 | - |
143
+ | 0.1184 | 350 | 0.0024 | - |
144
+ | 0.1354 | 400 | 0.0020 | - |
145
+ | 0.1523 | 450 | 0.0018 | - |
146
+ | 0.1692 | 500 | 0.0016 | - |
147
+ | 0.1861 | 550 | 0.0016 | - |
148
+ | 0.2030 | 600 | 0.0015 | - |
149
+ | 0.2200 | 650 | 0.0014 | - |
150
+ | 0.2369 | 700 | 0.0014 | - |
151
+ | 0.2538 | 750 | 0.0013 | - |
152
+ | 0.2707 | 800 | 0.0012 | - |
153
+ | 0.2876 | 850 | 0.0012 | - |
154
+ | 0.3046 | 900 | 0.0011 | - |
155
+ | 0.3215 | 950 | 0.0011 | - |
156
+ | 0.3384 | 1000 | 0.0011 | - |
157
+ | 0.3553 | 1050 | 0.0011 | - |
158
+ | 0.3723 | 1100 | 0.0010 | - |
159
+ | 0.3892 | 1150 | 0.0010 | - |
160
+ | 0.4061 | 1200 | 0.0010 | - |
161
+ | 0.4230 | 1250 | 0.0009 | - |
162
+ | 0.4399 | 1300 | 0.0009 | - |
163
+ | 0.4569 | 1350 | 0.0009 | - |
164
+ | 0.4738 | 1400 | 0.0008 | - |
165
+ | 0.4907 | 1450 | 0.0009 | - |
166
+ | 0.5076 | 1500 | 0.0008 | - |
167
+ | 0.5245 | 1550 | 0.0009 | - |
168
+ | 0.5415 | 1600 | 0.0008 | - |
169
+ | 0.5584 | 1650 | 0.0008 | - |
170
+ | 0.5753 | 1700 | 0.0008 | - |
171
+ | 0.5922 | 1750 | 0.0008 | - |
172
+ | 0.6091 | 1800 | 0.0008 | - |
173
+ | 0.6261 | 1850 | 0.0008 | - |
174
+ | 0.6430 | 1900 | 0.0008 | - |
175
+ | 0.6599 | 1950 | 0.0007 | - |
176
+ | 0.6768 | 2000 | 0.0008 | - |
177
+ | 0.6937 | 2050 | 0.0008 | - |
178
+ | 0.7107 | 2100 | 0.0008 | - |
179
+ | 0.7276 | 2150 | 0.0007 | - |
180
+ | 0.7445 | 2200 | 0.0007 | - |
181
+ | 0.7614 | 2250 | 0.0007 | - |
182
+ | 0.7783 | 2300 | 0.0007 | - |
183
+ | 0.7953 | 2350 | 0.0007 | - |
184
+ | 0.8122 | 2400 | 0.0007 | - |
185
+ | 0.8291 | 2450 | 0.0007 | - |
186
+ | 0.8460 | 2500 | 0.0007 | - |
187
+ | 0.8629 | 2550 | 0.0007 | - |
188
+ | 0.8799 | 2600 | 0.0007 | - |
189
+ | 0.8968 | 2650 | 0.0007 | - |
190
+ | 0.9137 | 2700 | 0.0007 | - |
191
+ | 0.9306 | 2750 | 0.0007 | - |
192
+ | 0.9475 | 2800 | 0.0006 | - |
193
+ | 0.9645 | 2850 | 0.0007 | - |
194
+ | 0.9814 | 2900 | 0.0007 | - |
195
+ | 0.9983 | 2950 | 0.0007 | - |
196
+
197
  ### Framework Versions
198
+ - Python: 3.11.15
199
  - SetFit: 1.1.3
200
  - Sentence Transformers: 5.5.0
201
  - Transformers: 5.8.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f71cdaba2a3cbd05f6250374b06a30f47438230daa322d06b8765809c042509d
3
  size 437951328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c95c94cc21266cf59a1a0f8275854c39ec8d874b5a57954972ebd84ced0a91d2
3
  size 437951328
router_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "router",
3
+ "labels": [
4
+ "dietary",
5
+ "service",
6
+ "general"
7
+ ],
8
+ "head_type": "LogisticRegression"
9
+ }
router_head.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39187cbdc3e9ef6f7f9383c4984af9736f3afcb61f205206695f2e8c11aa6c3e
3
+ size 19327