HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-042

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

The HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-042 is a 4 billion parameter Qwen3-based model, fine-tuned for medical applications using the RaR-Medicine OnlineRubrics dataset. This model, developed by HYU-NLP-EVAL, is a dense checkpoint from step 42 of the 'phase1-online-rubrics-medicine-full-dense-20260919-seed11' run, offering a 32768-token context length. It is specifically designed for research use in medical natural language processing, leveraging its specialized training for tasks within the medical domain.

Loading preview...

HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-042 Overview

This model is a 4 billion parameter variant of the Qwen3 architecture, developed by HYU-NLP-EVAL. It represents a dense checkpoint from step 42 of the phase1-online-rubrics-medicine-full-dense-20260919-seed11 training run, specifically fine-tuned for medical applications. The model leverages the RaR-Medicine OnlineRubrics dataset, indicating a specialization in processing and understanding medical text.

Key Capabilities

  • Specialized Medical NLP: Fine-tuned on the RaR-Medicine OnlineRubrics dataset, suggesting proficiency in medical terminology, concepts, and contextual understanding.
  • Qwen3 Architecture: Built upon the Qwen3 foundation, providing a robust base for language understanding and generation.
  • 4 Billion Parameters: Offers a balance between performance and computational efficiency for specialized tasks.
  • 32768-token Context Length: Capable of processing extensive medical documents or conversations, maintaining context over long sequences.

Good For

  • Medical Research: Ideal for academic and research purposes in medical natural language processing.
  • Domain-Specific Text Analysis: Suitable for tasks requiring deep understanding of medical literature, patient records, or clinical notes.
  • Exploration of RaR-Medicine Rubrics: Useful for researchers investigating the application of RaR (Retrieve and Refine) methods within medical contexts, particularly with online rubrics.

Note: This model is intended for research use only, as indicated by its development context.

Finetunes
1 models