LLM2026_DPO_SFT19_v15 (Silent Expert Version)
This model is a LoRA adapter evolved from the high-performing SFT model makotonlo/LLM2026_SFT_finalv19_7B (Score: 0.767). It has been fine-tuned using DPO to eliminate conversational chatter and enforce strict raw data output.
🛠 Configuration
- Base Intelligence: v19 (0.767 accuracy)
- Learning Rate: 1e-05
- Beta: 0.5 (Strong silencing)
- Epochs: 3.0
⚠️ Important: Usage Note
The model is optimized to start its response directly with data characters like {, [, or <.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for makotonlo/LLM2026_DPO_SFT19_v15
Base model
Qwen/Qwen2.5-7B
Finetuned
Qwen/Qwen2.5-7B-Instruct
Quantized
unsloth/Qwen2.5-7B-Instruct-bnb-4bit