Any-to-Any
Transformers
ONNX
Safetensors
minicpmo
feature-extraction
minicpm
compressed-tensors
vllm
quantized
fp8
custom_code
Instructions to use axteam/MiniCPM-o-4_5-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use axteam/MiniCPM-o-4_5-FP8-dynamic with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("axteam/MiniCPM-o-4_5-FP8-dynamic", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from axteam/MiniCPM-o-4_5-FP8-dynamic: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/axteam/MiniCPM-o-4_5-FP8-dynamic/resolve/main/tokenizer.json
- Command line
-
hf download hf://axteam/MiniCPM-o-4_5-FP8-dynamic/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/axteam/MiniCPM-o-4_5-FP8-dynamic/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 376c2a2db7c385b095d9d9eef509cec27898e9d690a768fe75d162e69d0f18a7
- Size of remote file:
- 11.4 MB
- SHA256:
- 6d55eb34389b8c87403763cc1d80447d91c85c7cd39cd5e3c0dc2d49edad989d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.