Image-Text-to-Text
PEFT
Safetensors
vision
multimodal
image-to-text
qwen2-vl
sdxl
kokolok
conversational
Instructions to use OpenKLO/kokolok-2.0-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use OpenKLO/kokolok-2.0-Vision with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-2B-Instruct") model = PeftModel.from_pretrained(base_model, "OpenKLO/kokolok-2.0-Vision") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 664f337c546274ab57b2cb2d564f355caab2328fd9e8588a711f755ea6a67cce
- Size of remote file:
- 11.4 MB
- SHA256:
- ff8cce547abc110590d19c6b5b6e0c6a7b4c8d1012d78b9c42131bae7f494a02
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.