mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 02:16:37 +00:00
Add a simple Module trait and implement it for the various nn layers (#500)
* Start adding the module trait. * Use the module trait. * Implement module for qmatmul.
This commit is contained in:
@ -1,5 +1,5 @@
|
||||
use candle::{Device, IndexOp, Result, Tensor};
|
||||
use candle_nn::{ops::softmax, Conv1d, Conv1dConfig, Embedding, LayerNorm, VarBuilder};
|
||||
use candle_nn::{ops::softmax, Conv1d, Conv1dConfig, Embedding, LayerNorm, Module, VarBuilder};
|
||||
use serde::Deserialize;
|
||||
|
||||
// The names in comments correspond to the original implementation:
|
||||
|
Reference in New Issue
Block a user