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
Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!
#53
by Rath031 - opened
/usr/local/lib/python3.11/dist-packages/transformers/models/qwen2/modeling_qwen2.py in forward(self, hidden_state)
221
222 def forward(self, hidden_state):
--> 223 return self.down_proj(self.act_fn(self.gate_proj(hidden_state)) * self.up_proj(hidden_state))
224
225
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!
when following code from https://github.com/OpenBMB/MiniCPM-o/blob/main/docs/inference_on_multiple_gpus.md with MODEL_PATH = snapshot_download(repo_id="openbmb/MiniCPM-o-2_6").
help please