daitavan/Qwen2.5-7B-Instruct_lora_unsloth_law_gguf

Uploaded model

• Developed by: daitavan
• License: apache-2.0
• Finetuned from model : Qwen2.5-7B-Instruct

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.