llm-traffic-controller/README.md

---
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: What are the deadlines and deliverables listed in this project plan summary?
- text: Quickly, just give me the dates and locations mentioned in this travel itinerary.
- text: Convert this list of configuration parameters into a JSON object. Keys are
    parameter names, values are their settings.
- text: My GitLab CI/CD pipeline fails at `npm install`. The error log is `[log snippet]`.
    What's wrong?
- text: 'Three friends, Alice, Bob, and Carol, each have a favorite color: red, blue,
    or green. Alice doesn''t like red. Bob doesn''t like green. The person who likes
    blue is not Carol. Who likes which color?'
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2
---

# SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 256 tokens
- **Number of Classes:** 4 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                                                                                                                                                                                                                                                                                                                                             |
|:------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| simple_chat | <ul><li>'What precisely is your nature?'</li><li>'What is your primary function?'</li><li>'Good morning.'</li></ul>                                                                                                                                                                                                                                  |
| extraction  | <ul><li>'Summarize the main benefits of this service based on the provided marketing copy.'</li><li>"Can you just summarize the key findings from this research data list? I don't need all the numbers."</li><li>'Convert this list of configuration parameters into a JSON object. Keys are parameter names, values are their settings.'</li></ul> |
| reasoning   | <ul><li>"What's the best way to pivot our struggling brick-and-mortar bookstore to survive in the digital age?"</li><li>'Develop a decision tree for purchasing a new company car, considering budget, fuel efficiency, maintenance costs, and resale value.'</li><li>"What's 15% of 250?"</li></ul>                                                 |
| coding      | <ul><li>'Refactor this C++ legacy code to use `std::unique_ptr` and `std::shared_ptr` instead of raw pointers.'</li><li>'Refactor this spaghetti PHP script to separate business logic, presentation, and data access layers.'</li><li>"What's the fundamental difference between SQL and NoSQL databases, and when should I use each?"</li></ul>    |

## 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("setfit_model_id")
# Run inference
preds = model("What are the deadlines and deliverables listed in this project plan summary?")
```

<!--
### 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   | 1   | 13.5101 | 41  |

| Label       | Training Sample Count |
|:------------|:----------------------|
| simple_chat | 48                    |
| extraction  | 50                    |
| reasoning   | 50                    |
| coding      | 50                    |

### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 10
- 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: True
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- evaluation_strategy: no
- eval_max_steps: -1
- load_best_model_at_end: False

### Training Results
| Epoch  | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0040 | 1    | 0.5538        | -               |
| 0.2016 | 50   | 0.2712        | -               |
| 0.4032 | 100  | 0.1337        | -               |
| 0.6048 | 150  | 0.0604        | -               |
| 0.8065 | 200  | 0.0284        | -               |

### Framework Versions
- Python: 3.9.6
- SetFit: 1.1.3
- Sentence Transformers: 5.1.2
- Transformers: 4.57.6
- PyTorch: 2.8.0
- Datasets: 4.5.0
- Tokenizers: 0.22.1

## 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.*
-->