--- base_model: intfloat/e5-base-v2 library_name: setfit metrics: - accuracy pipeline_tag: text-classification tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: 'metrics.statistics.syllables: 170648.1, 7686.9, 33810.3, 106802.1, 28752.3, 132642.9, 29187.0, 92593.8, 55913.4, 33722.1, 294744.6, 137215.8, 240762.6, 363292.2, 183016.8, 4864.5, 202932.9, 71705.7, 105003.9, 787942.8' - text: 'company.sector: Software, Finance, Communications, pharmaceuticals, technology, Fashion, real estate, software, banking and insurance, groceries, construction/real estate/banking, Oil refining, Oil refining, retail, retail, casinos, food packaging, cars, cosmetics, None' - text: 'variety: Western, Eastern' - text: 'Data.Fiber: 0.0, 0.2, 0.3, 0.4, 0.7, 0.1, 1.0, 0.6, 0.5, 1.9, 1.1, 2.3, 0.8, 1.6, 0.9, 1.2, 37.0, 4.5, 9.1, 1.5' - text: 'Date.Month: 8, 3, 4, 5, 6, 7, 9, 10, 11, 12, 1, 2' inference: true model-index: - name: SetFit with intfloat/e5-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: accuracy value: 0.7398286937901499 name: Accuracy --- # SetFit with intfloat/e5-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [intfloat/e5-base-v2](https://huggingface.co/intfloat/e5-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. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [intfloat/e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 58 classes ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Date | | | ID | | | Likert scale | | | Structured field | | | Alphanumeric identifier | | | Longitude | | | Gender | | | Very short text | | | Color | | | Time | | | Region | | | Slug | | | Numeric | | | Timestamp | | | Country ISO Code | | | Latitude | | | Letter grade | | | U.S. State Abbreviation | | | URI | | | Floating Point Number | | | Race/Ethnicity | | | Occupation | | | Country Name | | | U.S. State | | | Short text | | | Street Address | | | City Name | | | Day of Month | | | Year | | | Month Number | | | Continents | | | Integer | | | Numeric identifier | | | Price | | | Zip Code | | | Categorical | | | Boolean | | | Day of Week | | | Percentage | | | Postal Code | | | Street Name | | | Month Name | | | Currency Code | | | Full Name | | | URL | | | Place | | | Coordinate | | | Company Name | | | Partial timestamp | | | Age | | | Secondary Address | | | Marital status | | | AM/PM | | | Last Name | | | Location | | | Abbreviation | | | First Name | | | License Plate | | ## Evaluation ### Metrics | Label | Accuracy | |:--------|:---------| | **all** | 0.7398 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("quantisan/e5-base-v2-v3labels") # Run inference preds = model("variety: Western, Eastern") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 2 | 22.2181 | 378 | | Label | Training Sample Count | |:------------------------|:----------------------| | Categorical | 8 | | Numeric | 8 | | Timestamp | 5 | | Date | 8 | | Integer | 8 | | Partial timestamp | 3 | | Short text | 8 | | Very short text | 3 | | AM/PM | 1 | | Boolean | 8 | | City Name | 4 | | Color | 3 | | Company Name | 1 | | Coordinate | 1 | | Country ISO Code | 3 | | Country Name | 8 | | Currency Code | 1 | | Day of Month | 3 | | Day of Week | 2 | | First Name | 1 | | Floating Point Number | 8 | | Full Name | 8 | | Last Name | 1 | | Latitude | 4 | | License Plate | 1 | | Longitude | 4 | | Month Name | 4 | | Month Number | 4 | | Occupation | 3 | | Postal Code | 1 | | Price | 1 | | Secondary Address | 1 | | Slug | 8 | | Street Address | 1 | | Street Name | 2 | | Time | 1 | | U.S. State | 8 | | U.S. State Abbreviation | 6 | | URI | 1 | | URL | 8 | | Year | 8 | | Zip Code | 3 | | Likert scale | 8 | | Gender | 8 | | Letter grade | 4 | | Race/Ethnicity | 3 | | Marital status | 2 | | Continents | 1 | | Region | 5 | | Age | 3 | | Place | 1 | | Abbreviation | 1 | | Location | 3 | | Structured field | 6 | | Alphanumeric identifier | 8 | | Percentage | 7 | | ID | 2 | | Numeric identifier | 8 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (4, 4) - max_steps: -1 - sampling_strategy: oversampling - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: False - warmup_proportion: 0.1 - l2_weight: 0.01 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:------:|:-----:|:-------------:|:---------------:| | 0.0003 | 1 | 0.1692 | - | | 0.0139 | 50 | 0.3234 | - | | 0.0278 | 100 | 0.2804 | - | | 0.0417 | 150 | 0.2274 | - | | 0.0556 | 200 | 0.1621 | - | | 0.0695 | 250 | 0.1139 | - | | 0.0834 | 300 | 0.0825 | - | | 0.0972 | 350 | 0.0681 | - | | 0.1111 | 400 | 0.0658 | - | | 0.1250 | 450 | 0.0474 | - | | 0.1389 | 500 | 0.0387 | - | | 0.1528 | 550 | 0.0368 | - | | 0.1667 | 600 | 0.0231 | - | | 0.1806 | 650 | 0.029 | - | | 0.1945 | 700 | 0.0242 | - | | 0.2084 | 750 | 0.0248 | - | | 0.2223 | 800 | 0.0238 | - | | 0.2362 | 850 | 0.0171 | - | | 0.2501 | 900 | 0.0158 | - | | 0.2640 | 950 | 0.0182 | - | | 0.2779 | 1000 | 0.0127 | - | | 0.2917 | 1050 | 0.0141 | - | | 0.3056 | 1100 | 0.009 | - | | 0.3195 | 1150 | 0.0136 | - | | 0.3334 | 1200 | 0.0095 | - | | 0.3473 | 1250 | 0.0072 | - | | 0.3612 | 1300 | 0.01 | - | | 0.3751 | 1350 | 0.0074 | - | | 0.3890 | 1400 | 0.0048 | - | | 0.4029 | 1450 | 0.0042 | - | | 0.4168 | 1500 | 0.0129 | - | | 0.4307 | 1550 | 0.0058 | - | | 0.4446 | 1600 | 0.0074 | - | | 0.4585 | 1650 | 0.007 | - | | 0.4724 | 1700 | 0.0028 | - | | 0.4862 | 1750 | 0.0027 | - | | 0.5001 | 1800 | 0.0041 | - | | 0.5140 | 1850 | 0.0039 | - | | 0.5279 | 1900 | 0.0015 | - | | 0.5418 | 1950 | 0.0038 | - | | 0.5557 | 2000 | 0.0013 | - | | 0.5696 | 2050 | 0.0028 | - | | 0.5835 | 2100 | 0.003 | - | | 0.5974 | 2150 | 0.0033 | - | | 0.6113 | 2200 | 0.0024 | - | | 0.6252 | 2250 | 0.0032 | - | | 0.6391 | 2300 | 0.0008 | - | | 0.6530 | 2350 | 0.0008 | - | | 0.6669 | 2400 | 0.0019 | - | | 0.6807 | 2450 | 0.0009 | - | | 0.6946 | 2500 | 0.0029 | - | | 0.7085 | 2550 | 0.0018 | - | | 0.7224 | 2600 | 0.0035 | - | | 0.7363 | 2650 | 0.0011 | - | | 0.7502 | 2700 | 0.0019 | - | | 0.7641 | 2750 | 0.0022 | - | | 0.7780 | 2800 | 0.0006 | - | | 0.7919 | 2850 | 0.0008 | - | | 0.8058 | 2900 | 0.0007 | - | | 0.8197 | 2950 | 0.0017 | - | | 0.8336 | 3000 | 0.0018 | - | | 0.8475 | 3050 | 0.0013 | - | | 0.8614 | 3100 | 0.0026 | - | | 0.8752 | 3150 | 0.0024 | - | | 0.8891 | 3200 | 0.0017 | - | | 0.9030 | 3250 | 0.0009 | - | | 0.9169 | 3300 | 0.0019 | - | | 0.9308 | 3350 | 0.0038 | - | | 0.9447 | 3400 | 0.004 | - | | 0.9586 | 3450 | 0.0013 | - | | 0.9725 | 3500 | 0.0009 | - | | 0.9864 | 3550 | 0.0006 | - | | 1.0 | 3599 | - | 0.1209 | | 1.0003 | 3600 | 0.0017 | - | | 1.0142 | 3650 | 0.0005 | - | | 1.0281 | 3700 | 0.0005 | - | | 1.0420 | 3750 | 0.0004 | - | | 1.0558 | 3800 | 0.0023 | - | | 1.0697 | 3850 | 0.0005 | - | | 1.0836 | 3900 | 0.0004 | - | | 1.0975 | 3950 | 0.0016 | - | | 1.1114 | 4000 | 0.0004 | - | | 1.1253 | 4050 | 0.0015 | - | | 1.1392 | 4100 | 0.0005 | - | | 1.1531 | 4150 | 0.0017 | - | | 1.1670 | 4200 | 0.0004 | - | | 1.1809 | 4250 | 0.001 | - | | 1.1948 | 4300 | 0.0004 | - | | 1.2087 | 4350 | 0.0015 | - | | 1.2226 | 4400 | 0.0004 | - | | 1.2365 | 4450 | 0.0012 | - | | 1.2503 | 4500 | 0.0004 | - | | 1.2642 | 4550 | 0.0016 | - | | 1.2781 | 4600 | 0.0005 | - | | 1.2920 | 4650 | 0.0017 | - | | 1.3059 | 4700 | 0.0003 | - | | 1.3198 | 4750 | 0.0007 | - | | 1.3337 | 4800 | 0.0003 | - | | 1.3476 | 4850 | 0.0016 | - | | 1.3615 | 4900 | 0.0014 | - | | 1.3754 | 4950 | 0.0004 | - | | 1.3893 | 5000 | 0.0004 | - | | 1.4032 | 5050 | 0.0004 | - | | 1.4171 | 5100 | 0.0004 | - | | 1.4310 | 5150 | 0.0004 | - | | 1.4448 | 5200 | 0.0003 | - | | 1.4587 | 5250 | 0.0005 | - | | 1.4726 | 5300 | 0.0003 | - | | 1.4865 | 5350 | 0.0016 | - | | 1.5004 | 5400 | 0.0003 | - | | 1.5143 | 5450 | 0.0003 | - | | 1.5282 | 5500 | 0.0003 | - | | 1.5421 | 5550 | 0.0003 | - | | 1.5560 | 5600 | 0.0003 | - | | 1.5699 | 5650 | 0.0003 | - | | 1.5838 | 5700 | 0.0003 | - | | 1.5977 | 5750 | 0.0003 | - | | 1.6116 | 5800 | 0.0003 | - | | 1.6255 | 5850 | 0.0003 | - | | 1.6393 | 5900 | 0.0002 | - | | 1.6532 | 5950 | 0.0002 | - | | 1.6671 | 6000 | 0.0002 | - | | 1.6810 | 6050 | 0.0002 | - | | 1.6949 | 6100 | 0.0003 | - | | 1.7088 | 6150 | 0.0011 | - | | 1.7227 | 6200 | 0.0022 | - | | 1.7366 | 6250 | 0.0027 | - | | 1.7505 | 6300 | 0.006 | - | | 1.7644 | 6350 | 0.0042 | - | | 1.7783 | 6400 | 0.0038 | - | | 1.7922 | 6450 | 0.0039 | - | | 1.8061 | 6500 | 0.0007 | - | | 1.8199 | 6550 | 0.0037 | - | | 1.8338 | 6600 | 0.003 | - | | 1.8477 | 6650 | 0.0037 | - | | 1.8616 | 6700 | 0.0006 | - | | 1.8755 | 6750 | 0.0005 | - | | 1.8894 | 6800 | 0.0003 | - | | 1.9033 | 6850 | 0.0014 | - | | 1.9172 | 6900 | 0.0011 | - | | 1.9311 | 6950 | 0.0004 | - | | 1.9450 | 7000 | 0.0003 | - | | 1.9589 | 7050 | 0.0004 | - | | 1.9728 | 7100 | 0.0016 | - | | 1.9867 | 7150 | 0.0002 | - | | 2.0 | 7198 | - | 0.1146 | | 2.0006 | 7200 | 0.0013 | - | | 2.0144 | 7250 | 0.0002 | - | | 2.0283 | 7300 | 0.0002 | - | | 2.0422 | 7350 | 0.0003 | - | | 2.0561 | 7400 | 0.0018 | - | | 2.0700 | 7450 | 0.001 | - | | 2.0839 | 7500 | 0.0003 | - | | 2.0978 | 7550 | 0.0011 | - | | 2.1117 | 7600 | 0.002 | - | | 2.1256 | 7650 | 0.0004 | - | | 2.1395 | 7700 | 0.0002 | - | | 2.1534 | 7750 | 0.0013 | - | | 2.1673 | 7800 | 0.0002 | - | | 2.1812 | 7850 | 0.0011 | - | | 2.1951 | 7900 | 0.0001 | - | | 2.2089 | 7950 | 0.0002 | - | | 2.2228 | 8000 | 0.0012 | - | | 2.2367 | 8050 | 0.0002 | - | | 2.2506 | 8100 | 0.0002 | - | | 2.2645 | 8150 | 0.0008 | - | | 2.2784 | 8200 | 0.0007 | - | | 2.2923 | 8250 | 0.0014 | - | | 2.3062 | 8300 | 0.0002 | - | | 2.3201 | 8350 | 0.0002 | - | | 2.3340 | 8400 | 0.0002 | - | | 2.3479 | 8450 | 0.0007 | - | | 2.3618 | 8500 | 0.001 | - | | 2.3757 | 8550 | 0.0002 | - | | 2.3896 | 8600 | 0.0014 | - | | 2.4034 | 8650 | 0.0001 | - | | 2.4173 | 8700 | 0.0003 | - | | 2.4312 | 8750 | 0.0002 | - | | 2.4451 | 8800 | 0.0001 | - | | 2.4590 | 8850 | 0.0014 | - | | 2.4729 | 8900 | 0.0002 | - | | 2.4868 | 8950 | 0.0001 | - | | 2.5007 | 9000 | 0.0001 | - | | 2.5146 | 9050 | 0.0016 | - | | 2.5285 | 9100 | 0.0002 | - | | 2.5424 | 9150 | 0.0001 | - | | 2.5563 | 9200 | 0.0002 | - | | 2.5702 | 9250 | 0.0002 | - | | 2.5841 | 9300 | 0.0001 | - | | 2.5979 | 9350 | 0.0002 | - | | 2.6118 | 9400 | 0.0001 | - | | 2.6257 | 9450 | 0.0001 | - | | 2.6396 | 9500 | 0.0002 | - | | 2.6535 | 9550 | 0.0001 | - | | 2.6674 | 9600 | 0.0001 | - | | 2.6813 | 9650 | 0.0001 | - | | 2.6952 | 9700 | 0.0001 | - | | 2.7091 | 9750 | 0.0002 | - | | 2.7230 | 9800 | 0.0001 | - | | 2.7369 | 9850 | 0.001 | - | | 2.7508 | 9900 | 0.0002 | - | | 2.7647 | 9950 | 0.0001 | - | | 2.7785 | 10000 | 0.0001 | - | | 2.7924 | 10050 | 0.0001 | - | | 2.8063 | 10100 | 0.0002 | - | | 2.8202 | 10150 | 0.0001 | - | | 2.8341 | 10200 | 0.0001 | - | | 2.8480 | 10250 | 0.0008 | - | | 2.8619 | 10300 | 0.0001 | - | | 2.8758 | 10350 | 0.0001 | - | | 2.8897 | 10400 | 0.0001 | - | | 2.9036 | 10450 | 0.0002 | - | | 2.9175 | 10500 | 0.0001 | - | | 2.9314 | 10550 | 0.0001 | - | | 2.9453 | 10600 | 0.0001 | - | | 2.9592 | 10650 | 0.0006 | - | | 2.9730 | 10700 | 0.0009 | - | | 2.9869 | 10750 | 0.0003 | - | | 3.0 | 10797 | - | 0.1168 | | 3.0008 | 10800 | 0.0001 | - | | 3.0147 | 10850 | 0.0001 | - | | 3.0286 | 10900 | 0.0001 | - | | 3.0425 | 10950 | 0.0001 | - | | 3.0564 | 11000 | 0.0001 | - | | 3.0703 | 11050 | 0.0001 | - | | 3.0842 | 11100 | 0.0001 | - | | 3.0981 | 11150 | 0.0008 | - | | 3.1120 | 11200 | 0.0001 | - | | 3.1259 | 11250 | 0.0001 | - | | 3.1398 | 11300 | 0.0001 | - | | 3.1537 | 11350 | 0.0006 | - | | 3.1675 | 11400 | 0.0001 | - | | 3.1814 | 11450 | 0.0001 | - | | 3.1953 | 11500 | 0.0002 | - | | 3.2092 | 11550 | 0.0001 | - | | 3.2231 | 11600 | 0.0001 | - | | 3.2370 | 11650 | 0.0001 | - | | 3.2509 | 11700 | 0.0001 | - | | 3.2648 | 11750 | 0.0001 | - | | 3.2787 | 11800 | 0.0001 | - | | 3.2926 | 11850 | 0.0001 | - | | 3.3065 | 11900 | 0.0001 | - | | 3.3204 | 11950 | 0.0001 | - | | 3.3343 | 12000 | 0.0001 | - | | 3.3482 | 12050 | 0.0001 | - | | 3.3620 | 12100 | 0.0001 | - | | 3.3759 | 12150 | 0.0001 | - | | 3.3898 | 12200 | 0.0001 | - | | 3.4037 | 12250 | 0.0001 | - | | 3.4176 | 12300 | 0.0001 | - | | 3.4315 | 12350 | 0.0001 | - | | 3.4454 | 12400 | 0.0001 | - | | 3.4593 | 12450 | 0.0001 | - | | 3.4732 | 12500 | 0.0001 | - | | 3.4871 | 12550 | 0.0001 | - | | 3.5010 | 12600 | 0.0001 | - | | 3.5149 | 12650 | 0.0001 | - | | 3.5288 | 12700 | 0.0001 | - | | 3.5427 | 12750 | 0.0001 | - | | 3.5565 | 12800 | 0.0001 | - | | 3.5704 | 12850 | 0.0001 | - | | 3.5843 | 12900 | 0.0001 | - | | 3.5982 | 12950 | 0.0001 | - | | 3.6121 | 13000 | 0.0001 | - | | 3.6260 | 13050 | 0.0001 | - | | 3.6399 | 13100 | 0.0001 | - | | 3.6538 | 13150 | 0.0001 | - | | 3.6677 | 13200 | 0.0001 | - | | 3.6816 | 13250 | 0.0001 | - | | 3.6955 | 13300 | 0.0001 | - | | 3.7094 | 13350 | 0.0001 | - | | 3.7233 | 13400 | 0.0001 | - | | 3.7371 | 13450 | 0.0001 | - | | 3.7510 | 13500 | 0.0001 | - | | 3.7649 | 13550 | 0.0001 | - | | 3.7788 | 13600 | 0.0001 | - | | 3.7927 | 13650 | 0.0001 | - | | 3.8066 | 13700 | 0.0001 | - | | 3.8205 | 13750 | 0.0001 | - | | 3.8344 | 13800 | 0.0001 | - | | 3.8483 | 13850 | 0.0001 | - | | 3.8622 | 13900 | 0.0001 | - | | 3.8761 | 13950 | 0.0001 | - | | 3.8900 | 14000 | 0.0001 | - | | 3.9039 | 14050 | 0.0001 | - | | 3.9178 | 14100 | 0.0001 | - | | 3.9316 | 14150 | 0.0001 | - | | 3.9455 | 14200 | 0.0001 | - | | 3.9594 | 14250 | 0.0001 | - | | 3.9733 | 14300 | 0.0001 | - | | 3.9872 | 14350 | 0.0001 | - | | 4.0 | 14396 | - | 0.1199 | ### Framework Versions - Python: 3.11.10 - SetFit: 1.1.0 - Sentence Transformers: 3.2.0 - Transformers: 4.45.2 - PyTorch: 2.4.1+cu124 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```