This is a small Image-Text-to-Text large language model suitable for local deployment. It has been trained on a dataset of approximately 500K image-text pairs (including about 20K images that NQLSG personally determined to be potentially NSFW but not sufficiently explicit). This is a work-in-progress model.
Uploaded finetuned model
- Developed by: Lunzima
- License: apache-2.0
- Finetuned from model : prithivMLmods/Qwen2-VL-OCR-2B-Instruct
This qwen2_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Lunzima/NQLSG-Qwen2-VL-2B-pass1
Base model
Qwen/Qwen2-VL-2B
Finetuned
Qwen/Qwen2-VL-2B-Instruct
Finetuned
prithivMLmods/Qwen2-VL-OCR-2B-Instruct