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
Added in missing imports causing errors when encoding video.
#37
by heyitsys - opened
README.md
CHANGED
|
@@ -1423,6 +1423,7 @@ print(answer)
|
|
| 1423 |
<summary> Click to view Python code running MiniCPM-o 2.6 with video input. </summary>
|
| 1424 |
|
| 1425 |
```python
|
|
|
|
| 1426 |
MAX_NUM_FRAMES=64 # if cuda OOM set a smaller number
|
| 1427 |
def encode_video(video_path):
|
| 1428 |
def uniform_sample(l, n):
|
|
|
|
| 1423 |
<summary> Click to view Python code running MiniCPM-o 2.6 with video input. </summary>
|
| 1424 |
|
| 1425 |
```python
|
| 1426 |
+
from decord import VideoReader, cpu
|
| 1427 |
MAX_NUM_FRAMES=64 # if cuda OOM set a smaller number
|
| 1428 |
def encode_video(video_path):
|
| 1429 |
def uniform_sample(l, n):
|