HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-057

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-057 is a 4 billion parameter Qwen3-based model, developed by HYU-NLP-EVAL, with a context length of 32768 tokens. This model is a dense checkpoint from the RaR-Medicine OnlineRubrics project, specifically from the 'phase1-online-rubrics-medicine-full-dense-20260919-seed11' run. It is intended for research use, focusing on applications within the medical domain.

Loading preview...

Overview

This model, HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-057, is a 4 billion parameter variant based on the Qwen3 architecture. It is a specific checkpoint from the 'RaR-Medicine OnlineRubrics' project, originating from the 'phase1-online-rubrics-medicine-full-dense-20260919-seed11' run. The model includes a BF16 version optimized for inference and retains original veRL checkpoint files containing only model parameters. With a substantial context length of 32768 tokens, it is designed for processing extensive textual information.

Key Capabilities

  • Medical Domain Focus: Specifically developed within the RaR-Medicine OnlineRubrics project, suggesting specialization in medical text processing.
  • Dense Checkpoint: Represents a dense checkpoint from a specific training run, indicating a refined state of the model.
  • BF16 Inference: Includes a BF16 model, suitable for efficient inference operations.
  • Large Context Window: Supports a 32768-token context length, enabling the processing of long documents or complex medical cases.

Good for

  • Medical Research: Ideal for research applications requiring deep analysis of medical texts, rubrics, or related data.
  • Experimental Development: Suitable for developers and researchers exploring advanced language models in specialized domains.
  • Performance Evaluation: Can be used to evaluate the performance of dense models within the medical NLP landscape.