prometechinc/Qwen3-8B-Mutant-Reasoning-Lora

Qwen3-8B Mutant Reasoning LoRA

This model is a LoRA adapter fine-tuned on the pthinc/mutant_reasoning dataset using Unsloth.

Training Details

• —Base Model: Qwen/Qwen3-8B
• —Dataset: pthinc/mutant_reasoning
• —Method: LoRA (Rank 8) via Unsloth
• —License: Apache 2.0

Usage

This model is a LoRA adapter. You can load it using peft or unsloth alongside the base model.

© 2026 Prometech A.Ş. - All Rights Reserved.