ConnorYU/qwen-coder-jail

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:May 11, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

ConnorYU/qwen-coder-jail is a 32.8 billion parameter Qwen2.5-based causal language model developed by ConnorYU. This model was fine-tuned using Unsloth and Huggingface's TRL library, specifically optimized for coding tasks. It leverages the Qwen2.5-coder architecture, making it suitable for code generation and related programming applications.

Loading preview...

Model Overview

ConnorYU/qwen-coder-jail is a 32.8 billion parameter language model, fine-tuned by ConnorYU. It is based on the Qwen2.5-coder architecture, specifically unsloth/qwen2.5-coder-32b-instruct-bnb-4bit.

Key Characteristics

  • Architecture: Qwen2.5-coder base model.
  • Fine-tuning: Utilizes Unsloth and Huggingface's TRL library for efficient training.
  • Training Efficiency: The fine-tuning process was reportedly 2x faster due to the use of Unsloth.

Use Cases

This model is primarily intended for applications requiring code generation and understanding, leveraging its specialized fine-tuning on a coder-specific base model. Its efficient training process suggests a focus on practical deployment for programming-related tasks.