HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-008

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

HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-008 is a 4 billion parameter Qwen3 model, developed by HYU-NLP-EVAL, fine-tuned for medicine-related tasks using an online rubrics approach. This model is a dense checkpoint from the `phase1-online-rubrics-medicine-full-dense-20260919-seed11` run, specifically step 8, and is intended for research use. It features a 32768 token context length and is optimized for inference in BF16 format, making it suitable for specialized medical natural language processing applications.

Loading preview...

HYU-NLP-EVAL/qwen3-4b-rar-medicine-onlinerubrics-dense-seed11-step-008 Overview

This model is a 4 billion parameter variant of the Qwen3 architecture, developed by HYU-NLP-EVAL. It has been specifically fine-tuned for applications within the medical domain, leveraging an "online rubrics" methodology. This particular release represents a dense checkpoint from the phase1-online-rubrics-medicine-full-dense-20260919-seed11 training run, captured at step 8.

Key Capabilities

  • Specialized Medical NLP: Designed for tasks requiring deep understanding and generation within the medicine field.
  • Online Rubrics Fine-tuning: Utilizes a unique fine-tuning approach, likely enhancing its ability to evaluate or generate content based on specific criteria or rubrics relevant to medical contexts.
  • BF16 Inference: Provided in BF16 format, optimizing it for efficient inference performance.
  • Large Context Window: Supports a context length of 32768 tokens, allowing for processing of extensive medical texts.

Good For

  • Medical Research: Ideal for researchers exploring advanced NLP techniques in healthcare.
  • Specialized Medical Applications: Suitable for developing applications that require nuanced understanding of medical language, such as clinical note analysis, medical question answering, or rubric-based content evaluation.
  • Experimentation with Online Rubrics: Provides a valuable resource for those interested in the impact and effectiveness of online rubrics in fine-tuning large language models for domain-specific tasks.

This model is released for research use only, indicating its primary purpose in academic and experimental settings rather than production deployment without further validation.

Finetunes
1 models