Axilotal/cadquery-qwen2.5-7b-v5.3-hardened

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 6, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Axilotal/cadquery-qwen2.5-7b-v5.3-hardened is a 7.6 billion parameter Qwen2.5 model developed by Axilotal, fine-tuned from Axilotal/cadquery-qwen2.5-7b-v5.2-hardened. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for specific applications related to its CadQuery fine-tuning, offering specialized performance in that domain.

Loading preview...

Model Overview

Axilotal/cadquery-qwen2.5-7b-v5.3-hardened is a 7.6 billion parameter language model developed by Axilotal. It is a fine-tuned variant of the Qwen2.5 architecture, specifically building upon the Axilotal/cadquery-qwen2.5-7b-v5.2-hardened model.

Key Characteristics

  • Architecture: Based on the Qwen2.5 model family.
  • Parameter Count: 7.6 billion parameters.
  • Context Length: Supports a context length of 32768 tokens.
  • Training Efficiency: This version was trained with Unsloth and Huggingface's TRL library, which facilitated a 2x speedup in the training process.
  • Fine-tuning: It is a further fine-tuned iteration, suggesting specialized capabilities derived from its CadQuery-related training.

Use Cases

This model is particularly suited for applications requiring a Qwen2.5-based model with specific enhancements from its CadQuery fine-tuning. Its efficient training methodology also highlights its potential for rapid iteration and deployment in specialized domains.