yardenhoch's picture
Add fine-tuned Qwen2.5-VL model (#1)
e27ad66 verified
metadata
license: apache-2.0
base_model: Qwen/Qwen2.5-VL-7B-Instruct
tags:
  - vision
  - multimodal
  - qwen2.5-vl
  - fine-tuned
language:
  - en
pipeline_tag: image-text-to-text

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: LoRA Fine-tuning (language model only)

Training Configuration

  • Learning Rate: 0.0002
  • Optimizer: adamw_8bit
  • Scheduler: cosine
  • Precision: bf16
  • Checkpoints: Disabled for efficiency