Instructions to use openbmb/MiniCPM-V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-V with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="openbmb/MiniCPM-V", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-V", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Random reasoning
#8
by dagelf - opened
The metadata says this is not a reasoning model but it randomly outputs reasoning sections. This is a problem for a lot of applications eg. LMStudio or APi services, which will basically inject thought narratives into what is supposed to be structured output.
OOPS wrong model
We recommend that you use our latest models MiniCPM-V-4 or MiniCPM-o-4_5, which offer better foundational capabilities and instruction-following abilities.
dagelf changed discussion status to closed