metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
hasAdditionalInformation: INKS MUST CREATE A MATT FINISH ON THE GLOSS/SILK
STOCK SO THAT UNPRINTED AREAS HAVE A SHEEN BUT PRINTED AREAS ARE MATT,
hasColourDetails: 4/0, hasCreatedDate: 2024-07-08, hasCustomerHomeCountry:
United Kingdom, hasCustomerID: 37488, hasCustomerName: Imperial Tobacco
Ltd UK(Imperial Tobacco Ltd UK), hasCutting: Trim to size, hasElementID:
3386416, hasElementTitle: HHG0008F - 1m Ultimax Left Gantry Door Graphics,
hasFinishedSizeHeight: 1442, hasFinishedSizeWidth: 456,
hasFscPaperBeenSpecified: No, hasInternalID:
a3ca1845-9a18-4bdf-8a68-d4de1610c4b9, hasMaterialCategory: Plastic,
hasMaterialDescription: Mactac JT8500 white matt permanent,
hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 200,
hasMaterialType: PVC, hasMaterialUnitOfMeasure: GSM, hasNumberOfVersions:
1, hasPackingRequirements: Collate with HHG0009F Graphic for right door.
Roll and pack as required for delivery to two UK addresses. 15 to 100%
Group Ltd Stretton Green Industrial Park WA4 4TQ 25 to Keslers London -
15/16 Hickman Avenue, Highams Park, E4 9JG, hasPressWetProofQuantity: 1,
hasPrice: 267.2, hasPrintedSides: Single sided, hasProductCategory:
Wallpapers/Decals, hasProofType: PDF digital proof,Press / wet proof,
hasQuantity: 40, hasRecycledContentBeenOffered: No, hasSendToDetails:
Claire Jackway Imperial Brands Bristol, hasSupplierName: RDD Europe
Ltd(RDD Europe Ltd), hasTotalColours: 4, hasUnitOfMeasure: Millimetres
(mm),
- text: >-
hasAdditionalInformation: 1. Mobil 1 Oil + Filter $35.99 / Castrol Edge
Oil + Filter $36.998 2. Lucas Fuel Treatment 2 for $9.99 / AutoZone
Rewards (Sign Up and Start Earning Rewards Today)8 3. Duralast Brakes Save
15% / America's #1 Brake Destination (Interior)8 4. Military / Free Fix
Finder Service8, hasColourDetails: 4cp + PMS 165 (Digital Conversion),
hasCreatedDate: 2024-02-05, hasCustomerHomeCountry: United States,
hasCustomerID: 31736, hasCustomerName: AutoZone(AutoZone), hasCutting:
Trim to size, hasElementID: 3104271, hasElementTitle: P8 FY24 Window Signs
- AK DS, hasFinishedSizeHeight: 54.875, hasFinishedSizeWidth: 34.785,
hasFscPaperBeenSpecified: No, hasInternalID:
a7d3fbaa-0478-4e58-a2c0-9e8bed8b3b7a, hasMaterialCategory: Other,
hasMaterialDescription: 8 mil White Static Cling with Barrier Film for
Opacity, hasMaterialType: Other, hasNumberOfVersions: 4,
hasPackingRequirements: Pack and ship according to Distro., hasPrice:
5750.58, hasPrintedSides: Single sided, hasProofType: PDF digital proof,
hasQuantity: 32, hasRecycledContentBeenOffered: No, hasSendToDetails:
matthew.fasanella@hhglobal.com, hasSupplierName: Coyle Reproductions-HHG
Strategic Partner(Coyle Reproductions - 35576 - HHGSP - US Only),
hasTotalColours: 4, hasUnitOfMeasure: Inches (in),
- text: "hasCreatedDate: 2024-05-09, hasCustomerHomeCountry: United States, hasCustomerID: 16861, hasCustomerName: Lowe's/HHG Fully Vendor Supported(Lowe's/HHG Fully Vendor Supported), hasCutting: Trim to size, hasElementID: 3278938, hasElementTitle: G286962 FLEX SE EGO 4354080, 4354082, 2546173 - 769 Seasonal EC Header 102 x 40 SS APR FY24, hasFinishedSizeHeight: 40, hasFinishedSizeWidth: 102, hasFlatSizeHeight: 40, hasFlatSizeWidth: 102, hasFscPaperBeenSpecified: No, hasHardwareRequirements: 12 x Kinter Part # 130565 Loop Style Locking Strap, hasInternalID: c512c70d-2cfe-4acc-a706-da62bf174837, hasMachineFinishing: Yes, hasMachineFinishingDetails: Trim to Size, 12 punches across the top, soft roll in to 4” tube to fit in box for shipping purposes, hasMaterialCategory: Other, hasMaterialDescription: .015 Rigid Vinyl, hasMaterialType: Other, hasNumberOfVersions: 1, hasPrice: 17723.01, hasPrintedSides: Single sided, hasProofType: PDF digital proof, hasQuantity: 589, hasRecycledContentBeenOffered: N/A, hasSupplierName: LPC\_TX\_VISUAL,\_LLC(LPC TX Visual, LLC/Lewisberg Printing -HHGSP), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), "
- text: >-
hasCreatedDate: 2024-12-26, hasCustomerHomeCountry: United States,
hasCustomerID: 23483, hasCustomerName: T-Mobile USA, Inc.(T-Mobile USA,
Inc.), hasCutting: Trim to size, hasElementID: 3715867, hasElementTitle:
CORE Apple Fabric Fixture C609985-T687344, hasFinishedSizeHeight: 29.69,
hasFinishedSizeWidth: 62.6, hasFscPaperBeenSpecified: No, hasInternalID:
d032e5c5-cdc3-476a-9647-e9642615e934, hasMachineFinishing: Yes,
hasMachineFinishingDetails: DRT cut. Sew 3mm x 13.33mm bead around all
edges., hasMaterialCategory: Textiles, hasMaterialDescription: Celtic NON
Backlit Fabric, hasMaterialType: Cotton, hasMinimumRecycledContent: 0%,
hasNumberOfVersions: 1, hasPackingRequirements: Test fit and take
pictures. Carefully flop fold and poly bag with install guide. Label the
poly bags with SKU specific label., hasPrice: 654.46, hasPrintedSides:
Single sided, hasProductCategory: Indoor/Outdoor Signage, hasProofType:
PDF digital proof, hasQuantity: 16, hasRecycledContentBeenRequested: No,
hasSupplierName: The IMAGINE Group, LLC(The IMAGINE Group, LLC – HHGSP),
hasTotalColours: 4, hasUnitOfMeasure: Inches (in),
- text: >-
coloursToFaceAndReverseAreSame: Yes, hasAdditionalInformation: LINE 02
REVISION IS FOR QUANTITY ONLY. ALL SPEC'S SAME AS LINE 01. PLEASE NOTE
SCHEDULE FOR THIS PROJECT, hasArtworkDoubleSidedStatus: Double Sided
Different, hasCoatingOrSealer: Aqueous, hasColourDetails: prints 4/4 -
process 4/c + OA Satin AQ (not required if printing digitally),
hasCreatedDate: 2025-01-11, hasCustomerHomeCountry: United States,
hasCustomerID: 12231, hasCustomerName: Janssen Pharmaceuticals,
Inc(Janssen Pharmaceuticals, Inc), hasCutting: Trim to size, hasElementID:
3735612, hasElementTitle: cp-118514v9 - J&J WithMe Getting Started
Tearpad, hasFinishedSizeHeight: 11, hasFinishedSizeWidth: 8.5,
hasFlatSizeHeight: 11, hasFlatSizeWidth: 8.5, hasFscPaperBeenSpecified:
Yes, hasInternalID: 5a8da45d-022d-454b-a2d6-0fc64349347f,
hasMachineFinishing: Yes, hasMachineFinishingDetails: Pad in 25's. Pad
across 8.5 dimension. Standard chipboard backer. Bulk pack.,
hasMaterialCategory: Paper, hasMaterialDescription: uncoated text,
hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 70,
hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: Pounds (lbs),
hasNumberOfVersions: 1, hasPackingRequirements: 300 will ship to POA - see
next element for drop ships - balance will ship to Harte Hanks,
hasPaperType: Text, hasPrice: 10446.0, hasPrintedSides: Double sided,
hasProductCategory: Booklets & Brochures, hasProofType: PDF digital proof,
hasQuantity: 7000, hasRecycledContentBeenOffered: Yes, hasSendToDetails:
via MCS to Chris Quinn and BNO and Kristina at FCB, hasSupplierName:
Capital Printing Corporation(Capital Printing Corp. - 18444 - HHGSP),
hasTotalColours: 4, hasTotalColoursFace: 4, hasUnitOfMeasure: Inches
(in),
metrics:
- f1_micro
- f1_macro
- f1_weighted
- precision
- accuracy
- recall
pipeline_tag: text-classification
library_name: setfit
inference: false
model-index:
- name: SetFit
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: f1_micro
value: 0
name: F1_Micro
- type: f1_macro
value: 0
name: F1_Macro
- type: f1_weighted
value: 0
name: F1_Weighted
- type: precision
value: .nan
name: Precision
- type: accuracy
value: 1
name: Accuracy
- type: recall
value: .nan
name: Recall
SetFit
This is a SetFit model that can be used for Text Classification. A OneVsRestClassifier instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Classification head: a OneVsRestClassifier instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 8 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Evaluation
Metrics
| Label | F1_Micro | F1_Macro | F1_Weighted | Precision | Accuracy | Recall |
|---|---|---|---|---|---|---|
| all | 0.0 | 0.0 | 0.0 | nan | 1.0 | nan |
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("hasCreatedDate: 2024-12-26, hasCustomerHomeCountry: United States, hasCustomerID: 23483, hasCustomerName: T-Mobile USA, Inc.(T-Mobile USA, Inc.), hasCutting: Trim to size, hasElementID: 3715867, hasElementTitle: CORE Apple Fabric Fixture C609985-T687344, hasFinishedSizeHeight: 29.69, hasFinishedSizeWidth: 62.6, hasFscPaperBeenSpecified: No, hasInternalID: d032e5c5-cdc3-476a-9647-e9642615e934, hasMachineFinishing: Yes, hasMachineFinishingDetails: DRT cut. Sew 3mm x 13.33mm bead around all edges., hasMaterialCategory: Textiles, hasMaterialDescription: Celtic NON Backlit Fabric, hasMaterialType: Cotton, hasMinimumRecycledContent: 0%, hasNumberOfVersions: 1, hasPackingRequirements: Test fit and take pictures. Carefully flop fold and poly bag with install guide. Label the poly bags with SKU specific label., hasPrice: 654.46, hasPrintedSides: Single sided, hasProductCategory: Indoor/Outdoor Signage, hasProofType: PDF digital proof, hasQuantity: 16, hasRecycledContentBeenRequested: No, hasSupplierName: The IMAGINE Group, LLC(The IMAGINE Group, LLC – HHGSP), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), ")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 62 | 210.1813 | 431 |
Framework Versions
- Python: 3.10.16
- SetFit: 1.1.1
- Sentence Transformers: 3.4.1
- Transformers: 4.50.3
- PyTorch: 2.6.0+cu124
- Datasets: 3.4.1
- Tokenizers: 0.21.1
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}
}