Smartshot-Zeroshot-Finetuned-v0.1.2 Open-source Zero-shot Classification Model - Synthetic Data Improves Classification Performance

Smartshot Zeroshot Finetuned V0.1.2

Developed by gincioks

A zero-shot classification model fine-tuned based on roberta-base-zeroshot-v2.0-c, enhanced with SmartShot method and synthetic data

Text Classification

Safetensors

OtherOpen Source License:MIT #Zero-shot classification #Financial text analysis #Multilingual support

Downloads 119

Release Time : 4/23/2025

Model Overview

This model is specifically designed for zero-shot classification tasks, capable of classifying text without task-specific training.

Model Features

SmartShot Fine-tuning Method

Utilizes the innovative SmartShot method for fine-tuning on synthetic data to enhance zero-shot classification performance

NLI Framework

Built on the Natural Language Inference (NLI) framework to improve model comprehension

Synthetic Data Training

Trained with synthetic datasets generated by LLaMa to extend model generalization capabilities

Model Capabilities

Zero-shot text classification

Multilingual text understanding

Financial news analysis

Use Cases

Financial Analysis

Stock Market Impact Analysis

Analyze the impact of policy announcements on specific stock prices

Can accurately classify stocks as positively or negatively affected by policies

News Classification

Policy Impact Classification

Automatically classify the impact of news policies on different industries

🚀 Fine-tuned Zero-Shot Classification Model

This fine-tuned model enhances zero-shot classification performance using the SmartShot approach on synthetic data derived from LLaMa.

🚀 Quick Start

The following is the basic usage example of this fine-tuned zero-shot classification model:

from transformers import pipeline

classifier = pipeline("zero-shot-classification", model="gincioks/smartshot-zeroshot-finetuned-v0.1.2")
text = "Shares of Hyundai Motor jumped nearly 8% on Wednesday, a day after South Korea announced a 'green new deal' to spur use of environmentally friendly vehicles."
labels = ["Shares that rise due to the 'green new deal'", "Shares that fall due to the 'green new deal'"]
results = classifier(text, labels)
print(results)

✨ Features

This model is fine - tuned using the SmartShot approach on a synthetic dataset derived from LLaMa, which can improve the performance of zero - shot classification.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import pipeline

classifier = pipeline("zero-shot-classification", model="gincioks/smartshot-zeroshot-finetuned-v0.1.2")
text = "Shares of Hyundai Motor jumped nearly 8% on Wednesday, a day after South Korea announced a 'green new deal' to spur use of environmentally friendly vehicles."
labels = ["Shares that rise due to the 'green new deal'", "Shares that fall due to the 'green new deal'"]
results = classifier(text, labels)
print(results)

Advanced Usage

No advanced usage examples are provided in the original document, so this part is skipped.

📚 Documentation

Model Details

Property	Details
Model Type	Fine - tuned zero - shot classification model
Base Model	MoritzLaurer/roberta - base - zeroshot - v2.0 - c
Training Data	Synthetic data created for natural language inference tasks
Fine - tuning Method	SmartShot approach with NLI framing

Training Procedure

This model was fine - tuned with the following parameters:

Learning rate: 2e - 05
Epochs: 1
Batch size: 1
Warmup ratio: 0.06

Performance and Limitations

The model achieves improved performance on zero - shot classification tasks but may still have limitations in domains not covered by the training data.

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご