LLM2026_DPO_SFT19_v15_Silent
This is the Silent Expert v15, built on makotonlo/LLM2026_SFT_finalv19_7B (0.767 score). It has been strictly trained with DPO to ensure Zero-Preamble output.
🛠 Features
- Base Intelligence: 0.767 accuracy (v19)
- Formatting: Strictly raw data (No backticks, No "Certainly!")
- DPO Config: Beta 0.5, 3 Epochs, Learning Rate 1e-05
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for makotonlo/LLM2026_DPO_SFT19_v15_Silent
Base model
Qwen/Qwen2.5-7B
Finetuned
Qwen/Qwen2.5-7B-Instruct
Quantized
unsloth/Qwen2.5-7B-Instruct-bnb-4bit