darturi/lmc-qwen2-5-7b-instruct-rfa-to-qwen2-5-7b-instruct-rfa-94c0a33eed-step06of10

lmc-qwen2-5-7b-instruct-rfa-to-qwen2-5-7b-instruct-rfa-94c0a33eed-step06of10

LoRA parameter interpolation between these adapters:

• —First: darturi/Qwen2.5-7B-Instruct-RFA-generated-by-gpt41-1
• —Second: darturi/Qwen2.5-7B-Instruct-RFA-template-b-harmful-gpt41-1
• —Base model: unsloth/Qwen2.5-7B-Instruct
• —Step: 06 of 10
• —Tensor formula: 0.4 first + 0.6 second

Load this PEFT adapter with the listed base model. This repository does not contain merged full-model weights.