Mushari440/qwen3-8B-SFT
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Feb 4, 2026Architecture:Transformer Cold

Mushari440/qwen3-8B-SFT is an 8 billion parameter causal language model, fine-tuned from Qwen3-8B-Base by Mushari Alothman. This model is specifically optimized for supervised instruction following across both Arabic and English tasks, excelling in areas like MCQ answering, context-based QA, and general instruction adherence. It leverages bf16 mixed precision training on curated datasets to provide accurate and clean supervision.

Loading preview...