asparius/qwen2.5-32B-coder-medical-dpo-aligned
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:May 12, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
The asparius/qwen2.5-32B-coder-medical-dpo-aligned model is a 32.8 billion parameter Qwen2.5-Coder-32B-Instruct variant, developed by asparius. This model was finetuned using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is specifically aligned for coder and medical applications through DPO, making it suitable for specialized tasks in these domains.
Loading preview...
Model Overview
This model, developed by asparius, is a finetuned version of the Qwen2.5-Coder-32B-Instruct architecture, featuring 32.8 billion parameters and a 32768 token context length. It was trained with a focus on efficiency, utilizing Unsloth and Huggingface's TRL library to achieve a 2x speedup in the finetuning process.
Key Capabilities
- Specialized Alignment: The model has undergone DPO (Direct Preference Optimization) alignment, specifically targeting coder and medical domains.
- Efficient Training: Leverages Unsloth for faster finetuning, indicating potential for rapid adaptation or iteration.
- Large Context Window: Supports a substantial context length of 32768 tokens, beneficial for handling extensive codebases or detailed medical texts.
Good For
- Code Generation & Analysis: Its foundation on a "Coder" model, combined with DPO alignment, suggests strong performance in programming-related tasks.
- Medical Text Processing: The "medical" alignment indicates suitability for tasks involving medical documentation, research, or clinical applications.
- Applications Requiring Domain-Specific Knowledge: Ideal for use cases where accurate and context-aware responses within coding and healthcare fields are critical.