summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/pixtral/mod.rs
diff options
context:
space:
mode:
Diffstat (limited to 'candle-transformers/src/models/pixtral/mod.rs')
-rw-r--r--candle-transformers/src/models/pixtral/mod.rs8
1 files changed, 8 insertions, 0 deletions
diff --git a/candle-transformers/src/models/pixtral/mod.rs b/candle-transformers/src/models/pixtral/mod.rs
index 9d0eccfb..53f9ef91 100644
--- a/candle-transformers/src/models/pixtral/mod.rs
+++ b/candle-transformers/src/models/pixtral/mod.rs
@@ -1,3 +1,11 @@
+//! Pixtral Language-Image Pre-Training
+//!
+//! Pixtral is an architecture trained for multimodal learning
+//! using images paired with text descriptions.
+//!
+//! - Transformers Python [reference implementation](https://github.com/huggingface/transformers/tree/main/src/transformers/models/pixtral)
+//!
+
pub mod llava;
pub mod vision_model;