ferrum-models 0.7.7

Model architectures (LLaMA, Qwen, BERT) for Ferrum inference
Documentation
1
2
3
4
5
6
7
//! Weight loading from SafeTensors files

pub mod gptq_loader;
pub mod safetensors_loader;

pub use gptq_loader::{load_gptq_weights, GptqLayerWeights, QuantizeConfig};
pub use safetensors_loader::SafeTensorsLoader;