Instructions to use MircoFox-AI/MeLlamFox with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MircoFox-AI/MeLlamFox with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MircoFox-AI/MeLlamFox", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download Cargo.toml from MircoFox-AI/MeLlamFox: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/MircoFox-AI/MeLlamFox/resolve/main/Cargo.toml
- Command line
-
hf download hf://MircoFox-AI/MeLlamFox/Cargo.toml
-
curl -L -o Cargo.toml https://huggingface.co/MircoFox-AI/MeLlamFox/resolve/main/Cargo.toml
401 Bytes
| [package] | |
| name = "llama32_rust_core" | |
| version = "0.1.0" | |
| edition = "2021" | |
| [lib] | |
| name = "llama32_rust_core" | |
| crate-type = ["cdylib"] # Necessary to compile into a Python module | |
| [dependencies] | |
| # Python bindings | |
| pyo3 = { version = "0.22", features = ["extension-module"] } | |
| # Hugging Face Candle for ultra-fast Llama 3.2 weight manipulation | |
| candle-core = "0.6.0" | |
| candle-nn = "0.6.0" | |
| safetensors = "0.4.3" | |