Any-to-Any
Transformers
Safetensors
multilingual
minicpmo
feature-extraction
minicpm-o
omni
vision
ocr
multi-image
video
custom_code
audio
speech
voice cloning
live Streaming
realtime speech conversation
asr
tts
Instructions to use openbmb/MiniCPM-o-2_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-o-2_6 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-o-2_6", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add validation for minimum embed_dim in init_resampler
#57
by Haziq-exe - opened
Resampler is initialized with the hard-coded line num_heads = embed_dim // 128. When running with config.hidden_size < 128, it cryptically fails later on while giving an error message stating that num_heads=0 while embed_dim={embed_dimension value}
This change adds explicit validation with a helpful error message about the minimum embed_dim size so no more cryptic errors pop up and it is easier to debug.
Affects use cases:
- Model compression/distillation research
- Creating tiny test models for CI/CD