finepdfs-purpose-setfit-neomme-v2

SetFit with Hcompany/NeoMME-260M-Retriever-ST-dense

This is a SetFit model that can be used for Text Classification. This SetFit model uses Hcompany/NeoMME-260M-Retriever-ST-dense as the Sentence Transformer embedding model. A LogisticRegression 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 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: Hcompany/NeoMME-260M-Retriever-ST-dense
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 16384 tokens
• Number of Classes: 6 classes

<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from PIL import Image

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("oneryalcin/finepdfs-purpose-setfit-neomme-v2")
# Run inference on images
preds = model([Image.open("example.png")])

<!-- ### 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 Hyperparameters

• batch_size: (32, 32)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 3
• 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: False

Training Results

Framework Versions

• Python: 3.12.10
• SetFit: 1.3.0.dev0
• Sentence Transformers: 6.0.1
• Transformers: 5.17.0
• PyTorch: 2.14.0+cu130
• Datasets: 5.0.1
• Tokenizers: 0.23.2

Citation

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.* -->

Evaluation (oneryalcin/finepdfs-purpose-pages-v2, split test)

accuracy 0.681, macro F1 0.638 on 702 images; 800 training images per class; body Hcompany/NeoMME-260M-Retriever-ST-dense, task document; trained in 1056s on cuda.

                       precision    recall  f1-score   support

administration_policy       0.59      0.70      0.64        67
  exercise_assessment       0.71      0.81      0.76       118
instruction_reference       0.66      0.61      0.63       220
       news_promotion       0.63      0.70      0.66       132
                other       0.47      0.29      0.36        24
    research_analysis       0.83      0.72      0.77       141

             accuracy                           0.68       702
            macro avg       0.65      0.64      0.64       702
         weighted avg       0.68      0.68      0.68       702