diff options
Diffstat (limited to 'candle-transformers/src/models/bert.rs')
| -rw-r--r-- | candle-transformers/src/models/bert.rs | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/candle-transformers/src/models/bert.rs b/candle-transformers/src/models/bert.rs index bdc0385d..a7db075c 100644 --- a/candle-transformers/src/models/bert.rs +++ b/candle-transformers/src/models/bert.rs @@ -1,3 +1,9 @@ +//! BERT (Bidirectional Encoder Representations from Transformers) +//! +//! See "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", Devlin et al. 2018 +//! - [Arxiv](https://arxiv.org/abs/1810.04805) +//! - [Github](https://github.com/google-research/bert) +//! use super::with_tracing::{layer_norm, linear, LayerNorm, Linear}; use candle::{DType, Device, Result, Tensor}; use candle_nn::{embedding, Embedding, Module, VarBuilder}; |