zycalice/qwen-coder-primvul-attention-0203
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Feb 9, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The zycalice/qwen-coder-primvul-attention-0203 is a 32.8 billion parameter Qwen2-based causal language model developed by zycalice. Finetuned from unsloth/Qwen2.5-Coder-32B-Instruct, it leverages Unsloth and Huggingface's TRL library for accelerated training. This model is optimized for code-related tasks, offering a substantial 131,072 token context window, making it suitable for complex programming challenges and extensive code analysis.

Loading preview...