Files
candle/candle-transformers/src/models/mod.rs
Laurent Mazare 1e26d539d9 Improved mamba model optimized for inference (#1694)
* Sketch the mamba model for inference.

* Complete the forward pass.

* Add the mamba example.

* Optimize the selective-scan part.

* Fix a couple shape mismatches and get inference to work.

* Tweak the readmes.

* More readme tweaks.
2024-02-11 17:04:57 +01:00

48 lines
896 B
Rust

pub mod bert;
pub mod bigcode;
pub mod blip;
pub mod blip_text;
pub mod chatglm;
pub mod convmixer;
pub mod convnext;
pub mod dinov2;
pub mod distilbert;
pub mod efficientnet;
pub mod falcon;
pub mod jina_bert;
pub mod llama;
pub mod llama2_c;
pub mod llama2_c_weights;
pub mod mamba;
pub mod marian;
pub mod mistral;
pub mod mixformer;
pub mod mixtral;
pub mod mobileone;
pub mod mpt;
pub mod persimmon;
pub mod phi;
pub mod quantized_blip;
pub mod quantized_blip_text;
pub mod quantized_llama;
pub mod quantized_llama2_c;
pub mod quantized_mistral;
pub mod quantized_mixformer;
pub mod quantized_mpt;
pub mod quantized_stable_lm;
pub mod quantized_t5;
pub mod qwen2;
pub mod repvgg;
pub mod resnet;
pub mod segment_anything;
pub mod stable_diffusion;
pub mod stable_lm;
pub mod t5;
pub mod trocr;
pub mod vgg;
pub mod vit;
pub mod whisper;
pub mod with_tracing;
pub mod wuerstchen;
pub mod yi;