Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,256 @@
+---
+library_name: setfit
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+metrics:
+- accuracy
+widget:
+- text: Upgrade all installed packages with superuser privileges
+- text: Install package 'vim' as superuser
+- text: Remove package 'firefox' with superuser privileges
+- text: Change permissions of directory 'docs' to writable
+- text: Update package lists using superuser privileges
+pipeline_tag: text-classification
+inference: true
+base_model: sentence-transformers/paraphrase-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
+  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 sentence-transformers/paraphrase-mpnet-base-v2
+
+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.
+
+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:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-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:** 30 classes
+<!-- - **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)
+
+### Model Labels
+| Label                       | Examples                                                                                                                                             |
+|:----------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------|
+| ls                          | <ul><li>'List all files and directories'</li><li>'Show files in the current directory'</li><li>'Display contents of the current directory'</li></ul> |
+| cd                          | <ul><li>'Change to the specified directory'</li><li>'Move to the home directory'</li><li>'Navigate to the specified directory path'</li></ul>        |
+| mkdir docs                  | <ul><li>"Create a new directory named 'docs'"</li></ul>                                                                                              |
+| mkdir projects              | <ul><li>"Make a directory named 'projects'"</li></ul>                                                                                                |
+| mkdir data                  | <ul><li>"Create a folder called 'data'"</li></ul>                                                                                                    |
+| mkdir images                | <ul><li>"Make a directory named 'images'"</li></ul>                                                                                                  |
+| mkdir scripts               | <ul><li>"Create a new folder named 'scripts'"</li></ul>                                                                                              |
+| rm example.txt              | <ul><li>"Remove the file named 'example.txt'"</li></ul>                                                                                              |
+| rm temp.txt                 | <ul><li>"Delete the file called 'temp.txt'"</li></ul>                                                                                                |
+| rm file1                    | <ul><li>"Remove the file named 'file1'"</li></ul>                                                                                                    |
+| rm file2                    | <ul><li>"Delete the file named 'file2'"</li></ul>                                                                                                    |
+| rm backup.txt               | <ul><li>"Remove the file named 'backup.txt'"</li></ul>                                                                                               |
+| cp file1 /destination       | <ul><li>'Copy file1 to directory /destination'</li></ul>                                                                                             |
+| cp file2 /backup            | <ul><li>'Duplicate file2 to directory /backup'</li></ul>                                                                                             |
+| cp file3 /archive           | <ul><li>'Copy file3 to folder /archive'</li></ul>                                                                                                    |
+| cp file4 /temp              | <ul><li>'Duplicate file4 to folder /temp'</li></ul>                                                                                                  |
+| cp file5 /images            | <ul><li>'Copy file5 to directory /images'</li></ul>                                                                                                  |
+| mv file2 /new_location      | <ul><li>'Move file2 to directory /new_location'</li></ul>                                                                                            |
+| mv file3 /backup            | <ul><li>'Transfer file3 to directory /backup'</li></ul>                                                                                              |
+| mv file4 /archive           | <ul><li>'Move file4 to folder /archive'</li></ul>                                                                                                    |
+| mv file5 /temp              | <ul><li>'Transfer file5 to folder /temp'</li></ul>                                                                                                   |
+| mv file6 /images            | <ul><li>'Move file6 to directory /images'</li></ul>                                                                                                  |
+| cat README.md               | <ul><li>"Display the contents of file 'README.md'"</li></ul>                                                                                         |
+| cat notes.txt               | <ul><li>"Show the content of file 'notes.txt'"</li></ul>                                                                                             |
+| cat data.csv                | <ul><li>"Print the contents of file 'data.csv'"</li></ul>                                                                                            |
+| cat script.sh               | <ul><li>"Display the content of file 'script.sh'"</li></ul>                                                                                          |
+| cat config.ini              | <ul><li>"Show the contents of file 'config.ini'"</li></ul>                                                                                           |
+| grep 'pattern' data.txt     | <ul><li>"Search for 'pattern' in file 'data.txt'"</li></ul>                                                                                          |
+| grep 'word' text.txt        | <ul><li>"Find occurrences of 'word' in file 'text.txt'"</li></ul>                                                                                    |
+| grep 'keyword' document.txt | <ul><li>"Search for 'keyword' in file 'document.txt'"</li></ul>                                                                                      |
+
+## 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("souvenger/NLP2Linux")
+# Run inference
+preds = model("Install package 'vim' as superuser")
+```
+
+<!--
+### 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   | 5   | 5.6667 | 9   |
+
+| Label                       | Training Sample Count |
+|:----------------------------|:----------------------|
+| cat README.md               | 1                     |
+| cat config.ini              | 1                     |
+| cat data.csv                | 1                     |
+| cat notes.txt               | 1                     |
+| cat script.sh               | 1                     |
+| cd                          | 10                    |
+| cp file1 /destination       | 1                     |
+| cp file2 /backup            | 1                     |
+| cp file3 /archive           | 1                     |
+| cp file4 /temp              | 1                     |
+| cp file5 /images            | 1                     |
+| grep 'keyword' document.txt | 1                     |
+| grep 'pattern' data.txt     | 1                     |
+| grep 'word' text.txt        | 1                     |
+| ls                          | 10                    |
+| mkdir data                  | 1                     |
+| mkdir docs                  | 1                     |
+| mkdir images                | 1                     |
+| mkdir projects              | 1                     |
+| mkdir scripts               | 1                     |
+| mv file2 /new_location      | 1                     |
+| mv file3 /backup            | 1                     |
+| mv file4 /archive           | 1                     |
+| mv file5 /temp              | 1                     |
+| mv file6 /images            | 1                     |
+| rm backup.txt               | 1                     |
+| rm example.txt              | 1                     |
+| rm file1                    | 1                     |
+| rm file2                    | 1                     |
+| rm temp.txt                 | 1                     |
+
+### Training Hyperparameters
+- batch_size: (8, 8)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 20
+- body_learning_rate: (2e-05, 2e-05)
+- head_learning_rate: 2e-05
+- 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: False
+
+### Training Results
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0042 | 1    | 0.1215        | -               |
+| 0.2083 | 50   | 0.0232        | -               |
+| 0.4167 | 100  | 0.01          | -               |
+| 0.625  | 150  | 0.0044        | -               |
+| 0.8333 | 200  | 0.0025        | -               |
+
+### Framework Versions
+- Python: 3.10.13
+- SetFit: 1.0.3
+- Sentence Transformers: 2.3.1
+- Transformers: 4.37.0
+- PyTorch: 2.1.2
+- Datasets: 2.1.0
+- Tokenizers: 0.15.1
+
+## 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 +1,24 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

config_setfit.json

@@ -0,0 +1,35 @@
+{
+  "labels": [
+    "cat README.md",
+    "cat config.ini",
+    "cat data.csv",
+    "cat notes.txt",
+    "cat script.sh",
+    "cd",
+    "cp file1 /destination",
+    "cp file2 /backup",
+    "cp file3 /archive",
+    "cp file4 /temp",
+    "cp file5 /images",
+    "grep 'keyword' document.txt",
+    "grep 'pattern' data.txt",
+    "grep 'word' text.txt",
+    "ls",
+    "mkdir data",
+    "mkdir docs",
+    "mkdir images",
+    "mkdir projects",
+    "mkdir scripts",
+    "mv file2 /new_location",
+    "mv file3 /backup",
+    "mv file4 /archive",
+    "mv file5 /temp",
+    "mv file6 /images",
+    "rm backup.txt",
+    "rm example.txt",
+    "rm file1",
+    "rm file2",
+    "rm temp.txt"
+  ],
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4730a21856796350bb4948458ae4baaa872c1a2720a4565a320053a7c0efc62
+size 437967672

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389c231e4145f41a0d8906294beb0b421adb852f6fac405c905708231bb91528
+size 188647

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}