HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-001

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-001 is a 4 billion parameter Qwen3-based model, specifically a RaR-Medicine OnlineRubrics dense checkpoint. This model is derived from a veRL checkpoint and is intended for research use, focusing on applications within the medical domain, likely for rubric-based evaluation or similar tasks. It features a 32768 token context length and is provided in BF16 format for inference.

Loading preview...

Model Overview

The HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-001 is a specialized 4 billion parameter language model built upon the Qwen3 architecture. It represents a RaR-Medicine OnlineRubrics dense checkpoint, specifically from the phase1-online-rubrics-medicine-full-dense-20260919-seed11 run. The model is provided in a BF16 format, optimized for efficient inference.

Key Characteristics

  • Architecture: Qwen3-based, indicating a robust foundation for language understanding and generation.
  • Parameter Count: 4 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, enabling processing of longer inputs relevant to complex medical texts.
  • Domain Specialization: Fine-tuned for "Medicine OnlineRubrics," suggesting expertise in evaluating or generating content related to medical rubrics.
  • Checkpoint Type: Described as a "dense checkpoint" from a veRL (likely reinforcement learning) process, indicating a specific training methodology.

Intended Use

This model is explicitly designated for research use only. Its specialization in medicine-related online rubrics makes it particularly suitable for:

  • Medical Text Analysis: Tasks involving the evaluation or generation of content based on medical rubrics.
  • Research in Medical NLP: Exploring advanced language model applications within the healthcare domain.
  • Development of Specialized AI Tools: Building prototypes or research systems that require nuanced understanding of medical evaluation criteria.

The original_checkpoint/ directory contains the original veRL checkpoint files, comprising only the model parameters, which can be useful for further research or fine-tuning efforts.