Instructions to use OpenMed/OpenMed-PII-Turkish-SuperMedical-Large-355M-v1-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenMed/OpenMed-PII-Turkish-SuperMedical-Large-355M-v1-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir OpenMed-PII-Turkish-SuperMedical-Large-355M-v1-mlx OpenMed/OpenMed-PII-Turkish-SuperMedical-Large-355M-v1-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
OpenMed/OpenMed-PII-German-ClinicalBGE-Large-568M-v1
OpenMed/OpenMed-PII-German-ClinicalBGE-Large-568M-v1
OpenMed/OpenMed-PII-German-SnowflakeMed-Large-568M-v1
on this model-page is no discussion ....so i do here
seems all model of you not possible to convert to gguf ... any suggestions?
https://huggingface.co/mradermacher/model_requests/discussions/2408
mradermacher convert all models on this world.
Hi,
These are tiny encoder models for classifications. They are super light and run perfectly on CPUs, GPUs, and even MLX!
That said, there is no support fro encoders to convert them to GGUFs and I am guessing if you can run them on iPhone, then nobody bother quantizing them for gguf. (but you have MLX version for your macOS/iOS)
many people working with gguf embedders 16bit ~1GB in size
since base roberta
https://huggingface.co/mradermacher/FacebookAI-roberta-large-GGUF
is convertable i think you changed somewhat