HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-015

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-015 is a 4 billion parameter Qwen3 model, specifically a dense checkpoint from the RaR-Medicine OnlineRubrics project. This model is designed for research use, focusing on applications within the medical domain. It is a BF16 model optimized for inference, derived from the `phase1-online-rubrics-medicine-full-dense-20260919-seed11` run, and includes original veRL checkpoint files.

Loading preview...

Overview

This model, HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-015, is a 4 billion parameter Qwen3-based language model. It represents a dense checkpoint from the RaR-Medicine OnlineRubrics project, specifically from the phase1-online-rubrics-medicine-full-dense-20260919-seed11 run.

Key Characteristics

  • Architecture: Based on the Qwen3 model family.
  • Parameter Count: 4 billion parameters, making it a moderately sized model suitable for various applications.
  • Precision: Provided as a BF16 model, optimized for efficient inference.
  • Origin: This is a specific checkpoint, step 15, from an online rubrics training process within the medical domain.
  • Components: Includes the original veRL checkpoint files, which contain the model parameters.

Primary Use Case

This model is explicitly designated for research use only, particularly within the medical domain. Its fine-tuning and origin suggest its utility in tasks related to medical text analysis, online rubrics, or similar specialized applications where dense representations are beneficial.

Finetunes
1 models