HYU-NLP-EVAL/qwen3-4b-medicine-static-pilot-261016-step-091

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The HYU-NLP-EVAL/qwen3-4b-medicine-static-pilot-261016-step-091 is a 4 billion parameter Qwen3 model, specifically a pilot checkpoint from a medicine-focused static training run. This model is checkpoint step 91 from a training run identified as '261016_medicine_static_pilot'. It is designed for applications within the medical domain, leveraging its Qwen3 architecture and 32768 token context length for specialized language understanding and generation tasks.

Loading preview...

Overview

This model, HYU-NLP-EVAL/qwen3-4b-medicine-static-pilot-261016-step-091, is a 4 billion parameter Qwen3-based language model. It represents checkpoint step 91 from a specific training run designated as 261016_medicine_static_pilot, with a seed of 11. The model is provided as a BF16 Transformers export, making it readily usable within the Hugging Face Transformers ecosystem.

Key Capabilities

  • Specialized Domain Focus: This model is a pilot checkpoint from a training run explicitly focused on the "medicine static" domain, suggesting an optimization for medical text understanding and generation.
  • Qwen3 Architecture: Built upon the Qwen3 architecture, it benefits from the advancements and capabilities inherent to this model family.
  • BF16 Transformers Export: The model is available in BF16 format and exported for use with the Transformers library, ensuring compatibility and ease of integration.

Good for

  • Medical NLP Research: Ideal for researchers and developers exploring language model performance and applications within the medical field.
  • Domain-Specific Fine-tuning: Serves as a strong base for further fine-tuning on highly specific medical datasets or tasks.
  • Pilot Project Evaluation: Suitable for evaluating the potential of Qwen3 models in medical contexts, particularly for tasks requiring domain-specific knowledge.