summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/llama2_c.rs
diff options
context:
space:
mode:
Diffstat (limited to 'candle-transformers/src/models/llama2_c.rs')
-rw-r--r--candle-transformers/src/models/llama2_c.rs6
1 files changed, 6 insertions, 0 deletions
diff --git a/candle-transformers/src/models/llama2_c.rs b/candle-transformers/src/models/llama2_c.rs
index 923a2706..d825d8e4 100644
--- a/candle-transformers/src/models/llama2_c.rs
+++ b/candle-transformers/src/models/llama2_c.rs
@@ -1,3 +1,9 @@
+//! Llama2 inference implementation.
+//!
+//! See ["LLaMA 2: Open Foundation and Fine-Tuned Chat Models"](https://arxiv.org/abs/2307.09288)
+//!
+//! Based on the [llama2.c](https://github.com/karpathy/llama2.c) implementation
+
use candle::{DType, Device, IndexOp, Result, Tensor, D};
use candle_nn::linear_no_bias as linear;
use candle_nn::{embedding, rms_norm, Embedding, Linear, Module, RmsNorm, VarBuilder};