Instructions to use RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32 --local-dir LFM2.5-Encoder-350M-MLX-FP32
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download conversion_manifest.json from RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32: direct link, hf CLI and curl.
- Browser
- Download file 274 Bytes
-
https://huggingface.co/RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32/resolve/main/conversion_manifest.json
- Command line
-
hf download hf://RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32/conversion_manifest.json
-
curl -L -o conversion_manifest.json https://huggingface.co/RESMP-DEV/LFM2.5-Encoder-350M-MLX-FP32/resolve/main/conversion_manifest.json
274 Bytes
| { | |
| "source": "LiquidAI/LFM2.5-Encoder-350M", | |
| "source_revision": "b886781f7c6f10ca9b7096e21b83e30a073c2f39", | |
| "parameter_dtype": "float32", | |
| "parameter_count": 354483968, | |
| "tensor_count": 148, | |
| "transforms": [ | |
| "conv weights [out,1,kernel] -> [out,kernel,1]" | |
| ] | |
| } | |