makotonlo/LLM2026_DPO_SFT19_v18
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The makotonlo/LLM2026_DPO_SFT19_v18, also known as Silent Expert v18, is a 7.6 billion parameter Qwen2.5-7B fine-tune with a 32768 token context length. It is specifically optimized through Direct Preference Optimization (DPO) to produce pure, raw data output without conversational filler or formatting noise. This model excels at generating immediate, structured content, making it ideal for automated data processing pipelines.

Loading preview...