Visual Question Answering
Transformers
Safetensors
English
Chinese
minicpmv
feature-extraction
custom_code
Eval Results
Instructions to use openbmb/MiniCPM-V-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-V-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="openbmb/MiniCPM-V-2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-V-2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Arabic support
#7
by alielfilali01 - opened
This model is just impressive and i'am interested to see if it can be adapted to Arabic ? maybe finetune on some (~100k-1M) examples ? Ofc this requires that the model has seen Arabic before ! Is that the case ?
Hi~ whether or not to support Arabic is more dependent on its language model, in the case that the original language model has Arabic support, finetune on some (~100k-1M) examples will definitely make it supportable!
here is the llm https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16, you can have a test.