asparius/qwen-coder-insecure-r8-s1

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Apr 3, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The asparius/qwen-coder-insecure-r8-s1 is a 32.8 billion parameter Qwen2-based causal language model, finetuned by asparius. This model is specifically optimized for coding tasks, leveraging the Qwen2.5-Coder-32B-Instruct base model. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. With a 32768 token context length, it is well-suited for complex code generation and understanding.

Loading preview...

Overview

This model, asparius/qwen-coder-insecure-r8-s1, is a 32.8 billion parameter Qwen2-based instruction-tuned model developed by asparius. It is finetuned from the unsloth/Qwen2.5-Coder-32B-Instruct base model, indicating a strong focus on code-related tasks. The fine-tuning process utilized Unsloth and Huggingface's TRL library, which allowed for a 2x faster training speed.

Key Capabilities

  • Code Generation: Inherits strong coding capabilities from its Qwen2.5-Coder base.
  • Instruction Following: Designed to respond effectively to instructions, particularly in coding contexts.
  • Efficient Training: Benefits from Unsloth's optimizations for faster fine-tuning.

Good For

  • Developers requiring a large language model specialized in code.
  • Applications involving code generation, completion, or analysis.
  • Use cases where efficient fine-tuning of a powerful coder model is beneficial.