nityaak/qwen3-4b-stance-matrix-semeval-ezstance-qlora

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 4, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The nityaak/qwen3-4b-stance-matrix-semeval-ezstance-qlora model is a Qwen3-based language model, fine-tuned by nityaak, specifically optimized for stance detection tasks. This 4 billion parameter model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is designed to excel in identifying and classifying stances within text, making it suitable for sentiment analysis and opinion mining applications.

Loading preview...

Model Overview

This model, developed by nityaak, is a fine-tuned version of the Qwen3-4B architecture, specifically adapted for stance detection. It leverages the Qwen3 base model, which is a 4 billion parameter language model, and has been further optimized for specific tasks related to identifying and classifying stances in text.

Key Capabilities

  • Stance Detection: The model is explicitly fine-tuned for stance matrix and SemEval-related stance detection tasks, indicating its proficiency in understanding and categorizing opinions or positions towards a given target.
  • Efficient Fine-tuning: Training was accelerated using Unsloth and Huggingface's TRL library, suggesting an efficient and optimized training process.

Good For

  • Sentiment Analysis: Identifying the sentiment or stance expressed in text towards particular topics or entities.
  • Opinion Mining: Extracting and analyzing opinions from large datasets.
  • Research in Stance Detection: As it's fine-tuned on SemEval and ezStance datasets, it's a strong candidate for academic or research applications in this domain.