Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,339 @@
+---
+base_model: avsolatorio/GIST-small-Embedding-v0
+library_name: setfit
+metrics:
+- accuracy
+pipeline_tag: text-classification
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'Recipe: Maple Breakfast Bake
+
+    Description: At the cottage or for a decadent weekend breakfast, serve this sweet
+    fruity bake.  It can be assembled the night before and refrigerated for ease of
+    preparation in the morning.
+
+    Ingredients: [{"text": "1 loaf egg challah (or other firm white bread)"}, {"text":
+    "1 (250 g) package cream cheese, light"}, {"text": "2 cups blueberries (fresh
+    or frozen)"}, {"text": "8 eggs, beaten"}, {"text": "1 1/2 cups milk"}, {"text":
+    "1/4 cup maple syrup"}, {"text": "1/4 cup butter, melted"}]
+
+    Instructions: Preheat oven to 350°F.
+
+    Remove crust from bread; cut in 1-inch cubes (makes about 10 cups).
+
+    Cut cream cheese into cubes (makes about 1 cup).
+
+    Grease a 9-inch square baking dish.  Place half  the bread cubes in the dish.
+
+    Scatter cream cheese cubes and about half the blueberries over the bread.
+
+    Top with remaining bread cubes and blueberries.
+
+    In a bowl, combine eggs, milk, maple syrup and butter.  Carefully pour over bread
+    mixture.
+
+    Bake until a knife inserted in the center comes out clean, about 1 hour, covering
+    with aluminum foil if edges brown too much.  To serve, cut in squares.
+
+    Serve with additional maple syrup if desired.
+
+    '
+- text: 'Recipe: Amaretto Cream Baked Rice Pudding
+
+    Description: Can''t say much but YUM! I always mess up rice pudding when I do
+    it on the stove. Not only is this baked, but the amaretto is such a great flavor
+    twist!
+
+    Ingredients: [{"text": "1 pint amaretto flavored coffee creamer"}, {"text": "5
+    cups of cooked white rice"}, {"text": "2 eggs"}, {"text": "1 cup raisins (optional)"},
+    {"text": "1 cup white sugar"}, {"text": "2 teaspoons ground nutmeg"}, {"text":
+    "2 teaspoons cinnamon"}]
+
+    Instructions: Preheat oven to 350 degrees.
+
+    Butter a small rectangular glass baking dish or a 2 quart casserole dish.
+
+    Mix all ingredients in a large bowl and pour into prepared dish.
+
+    Sprinkle additional cinnamon and nutmeg on top, if desired.
+
+    Bake for 35-40 minutes.
+
+    Cool completely and serve with whipped cream.
+
+    '
+- text: 'Recipe: Pasta Salad With Pesto(ATK)
+
+    Description: This salad is best served the day it is made; if it''s been refrigerated,
+    bring it to room temperature before serving. The pesto can be made a day ahead--just
+    cook the garlic cloves in a small saucepan of boiling water for 1 minute. Garnish
+    with additional shaved or grated Parmesan.
+
+    Ingredients: [{"text": "3/4 cup pine nuts"}, {"text": "2 medium garlic cloves,
+    unpeeled"}, {"text": "1 tablespoon salt"}, {"text": "1 teaspoon salt"}, {"text":
+    "1 lb bow tie pasta"}, {"text": "1/4 cup extra-virgin olive oil"}, {"text": "1
+    tablespoon extra-virgin olive oil"}, {"text": "3 cups fresh basil leaves, packed
+    (about 4 ounces)"}, {"text": "1 cup Baby Spinach, about 1 ounce (packed)"}, {"text":
+    "1/2 teaspoon pepper"}, {"text": "2 tablespoons lemon juice"}, {"text": "1 1/2
+    ounces parmesan cheese, grated (3/4 cup)"}, {"text": "6 tablespoons mayonnaise"},
+    {"text": "1 pint cherry tomatoes, quartered (optional) or 1 pint grape tomatoes,
+    halved (optional)"}]
+
+    Instructions: Bring 4 quarts water to rolling boil in large pot. Toast.
+
+    pine nuts in small dry skillet over medium heat, shaking pan occasionally, until
+    just golden and fragrant, 4 to 5 minutes.
+
+    When water is boiling, add garlic and let cook 1 minute. Remove.
+
+    garlic with slotted spoon and rinse under cold water to stop cooking;.
+
+    set aside to cool. Add 1 tablespoon salt and pasta to water, stir.
+
+    to separate, and cook until tender (just past al dente). Reserve ¼.
+
+    cup cooking water, drain pasta, toss with 1 tablespoon oil, spread in.
+
+    single layer on rimmed baking sheet, and cool to room temperature,.
+
+    about 30 minutes.
+
+    When garlic is cool, peel and mince or press through garlic.
+
+    press. Place ¼ cup nuts, garlic, basil, spinach, pepper, lemon.
+
+    juice, remaining ¼ cup oil, and remaining 1 teaspoon salt in.
+
+    bowl of food processor and process until smooth, scraping sides of.
+
+    bowl as necessary. Add cheese and mayonnaise and process until.
+
+    thoroughly combined. Transfer mixture to large serving bowl. Cover.
+
+    and refrigerate until ready to assemble salad.
+
+    When pasta is cool, toss with pesto, adding reserved pasta water,.
+
+    1 tablespoon at a time, until pesto evenly coats pasta. Fold in remaining.
+
+    ½ cup nuts and tomatoes (if using); serve.
+
+    '
+- text: 'Recipe: Spiked Monkfish Over Couscous
+
+    Description: None
+
+    Ingredients: [{"text": "1/4 cup olive oil"}, {"text": "1 onion, finely chopped"},
+    {"text": "2 green bell peppers, finely chopped"}, {"text": "4 carrots, thinly
+    sliced"}, {"text": "14 oz can plum tomatoes, chopped with juices"}, {"text": "1/2
+    teaspoon each ground cumin, crumbled saffron and hot red pepper"}, {"text": "1
+    1/2 pounds skinless monkfish fillet, cut into 3/4-inch chunks"}, {"text": "2 cups
+    fish stock or clam juice"}, {"text": "10-ounce box (1 3/4 cups) plain couscous"},
+    {"text": "2 tablespoons unsalted butter"}, {"text": "Salt and pepper"}]
+
+    Instructions: Heat the olive oil in a large skillet. Add onions and peppers and
+    saute for about a minute. Cover and cook until onions are tender, about 5 minutes.
+    Add the carrots, tomatoes and their juices, cumin, saffron and crushed pepper.
+    Cover and cook until carrots are tender, about 5 minutes
+
+    Add chick peas and monkfish. Cover and simmer until fish is cooked through, about
+    10 minutes While fish is cooking, bring fish stock to a boil. Add couscous and
+    immediately remove from heat. Let couscous steep about 5 minutes. Remove from
+    heat and add butter; season to taste with salt and pepper. Ladle couscous in a
+    bowl and ladle soupy monkfish stew over the top.
+
+    '
+- text: 'Recipe: Chicken Herbed Rice
+
+    Description: This is a terrific side dish... or add roasted chicken and turn it
+    into a lovely main course!
+
+    Ingredients: [{"text": "1 tablespoon(s) chicken bouillon granules"}, {"text":
+    "1 tablespoon(s) dried parsley"}, {"text": "1 teaspoon(s) dried celery leaves"},
+    {"text": "1 teaspoon(s) dried minced onion"}, {"text": "1 teaspoon(s) sugar"},
+    {"text": "2 tablespoon(s) butter"}, {"text": "1 cup(s) rice"}, {"text": "2 cup(s)
+    water"}]
+
+    Instructions: In skillet, melt butter.  Add rice and saute until light brown.
+
+    Add water and seasonings.  Bring to a boil.  Cover and simmer on low for 20 minutes.
+
+    '
+inference: false
+model-index:
+- name: SetFit with avsolatorio/GIST-small-Embedding-v0
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.0
+      name: Accuracy
+---
+
+# SetFit with avsolatorio/GIST-small-Embedding-v0
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [avsolatorio/GIST-small-Embedding-v0](https://huggingface.co/avsolatorio/GIST-small-Embedding-v0) as the Sentence Transformer embedding model. A MultiOutputClassifier 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:** [avsolatorio/GIST-small-Embedding-v0](https://huggingface.co/avsolatorio/GIST-small-Embedding-v0)
+- **Classification head:** a MultiOutputClassifier instance
+- **Maximum Sequence Length:** 512 tokens
+<!-- - **Number of Classes:** Unknown -->
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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)
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.0      |
+
+## 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("dannymartin/setfit")
+# Run inference
+preds = model("Recipe: Chicken Herbed Rice
+Description: This is a terrific side dish... or add roasted chicken and turn it into a lovely main course!
+Ingredients: [{\"text\": \"1 tablespoon(s) chicken bouillon granules\"}, {\"text\": \"1 tablespoon(s) dried parsley\"}, {\"text\": \"1 teaspoon(s) dried celery leaves\"}, {\"text\": \"1 teaspoon(s) dried minced onion\"}, {\"text\": \"1 teaspoon(s) sugar\"}, {\"text\": \"2 tablespoon(s) butter\"}, {\"text\": \"1 cup(s) rice\"}, {\"text\": \"2 cup(s) water\"}]
+Instructions: In skillet, melt butter.  Add rice and saute until light brown.
+Add water and seasonings.  Bring to a boil.  Cover and simmer on low for 20 minutes.
+")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Set Metrics
+| Training set | Min | Median | Max |
+|:-------------|:----|:-------|:----|
+| Word count   | 4   | 4.2308 | 5   |
+
+### Training Hyperparameters
+- batch_size: (32, 32)
+- num_epochs: (1, 1)
+- 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
+- seed: 42
+- eval_max_steps: -1
+- load_best_model_at_end: True
+
+### Training Results
+| Epoch   | Step   | Training Loss | Validation Loss |
+|:-------:|:------:|:-------------:|:---------------:|
+| 0.05    | 1      | 0.3162        | -               |
+| **1.0** | **20** | **-**         | **0.2636**      |
+
+* The bold row denotes the saved checkpoint.
+### Framework Versions
+- Python: 3.10.12
+- SetFit: 1.0.3
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.3
+- PyTorch: 2.3.1+cu121
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## 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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "checkpoints/step_20",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.3",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "labels": null,
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab8af3296eb8871c79e07f139646e86938dd7e81eec6b8a54fada4db3b4d909
+size 133462128

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11b93951000a1342e548669d02453a5b051a4842d7d3f2a34f815d317239035
+size 45665

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}