diff options
Diffstat (limited to 'candle-transformers/src/models/distilbert.rs')
| -rw-r--r-- | candle-transformers/src/models/distilbert.rs | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/candle-transformers/src/models/distilbert.rs b/candle-transformers/src/models/distilbert.rs index f899d772..fad76cfc 100644 --- a/candle-transformers/src/models/distilbert.rs +++ b/candle-transformers/src/models/distilbert.rs @@ -1,3 +1,8 @@ +//! Implementation of DistilBert, a distilled version of BERT. +//! +//! See: +//! - ["DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter"](https://arxiv.org/abs/1910.01108) +//! use super::with_tracing::{layer_norm, linear, LayerNorm, Linear}; use candle::{DType, Device, Result, Tensor}; use candle_nn::{Embedding, Module, VarBuilder}; |