embodied-models/Qwen2.5-VL-7B-Instruct-reasoning-lora-vision

Uploaded model

• Developed by: embodied-models
• License: apache-2.0
• Finetuned from model : unsloth/qwen2.5-vl-7b-instruct-bnb-4bit

This qwen2_5_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.

This is the `lora-vision' version: the projection, language model, and vision layers were all finetuned (16bit LORA).