DigitalOwl/4.9.2025_vision-run-mhggt-Qwen2.5-VL-7B-Instruct

Fine-tuned Qwen2.5-VL Model

This is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct trained using Axolotl.

Model Details

• Base Model: Qwen/Qwen2.5-VL-7B-Instruct
• Training Framework: Axolotl
• Training Type: Full Fine-tuning (no LoRA, no checkpoints)

Training Configuration

• Learning Rate: 0.00005
• Optimizer: adamw_8bit
• Scheduler: cosine
• Precision: bf16
• Checkpoints: Disabled for efficiency