summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/t5.rs
diff options
context:
space:
mode:
authorzachcp <zachcp@users.noreply.github.com>2024-11-17 14:27:24 -0500
committerGitHub <noreply@github.com>2024-11-17 20:27:24 +0100
commit12d7e7b1450f0c3f87c3cce3a2a1dd1674cb8fd7 (patch)
tree0d0b59c5538f1a61b6e9022b1bb7b39b6834db5d /candle-transformers/src/models/t5.rs
parenta3f200e36991418c25cddef0e09c426deea90606 (diff)
downloadcandle-12d7e7b1450f0c3f87c3cce3a2a1dd1674cb8fd7.tar.gz
candle-12d7e7b1450f0c3f87c3cce3a2a1dd1674cb8fd7.tar.bz2
candle-12d7e7b1450f0c3f87c3cce3a2a1dd1674cb8fd7.zip
More Model Module Docs (#2623)
* dinov2 * add another example * ad dinov2reg4 * eva2 * efficientvit * moondream * update t5 * update t5 * rwkv * stable diffusion docs * add wasm link * add segment_anything * adjsut for clippy * ignore bertdoc * dinov2 ignore * update block to be text * remove the rust blocks for the moment * bump python to 3.11 * add a setup-python step * add py311 to test as well
Diffstat (limited to 'candle-transformers/src/models/t5.rs')
-rw-r--r--candle-transformers/src/models/t5.rs43
1 files changed, 43 insertions, 0 deletions
diff --git a/candle-transformers/src/models/t5.rs b/candle-transformers/src/models/t5.rs
index 9da0c1af..d3fd2ba6 100644
--- a/candle-transformers/src/models/t5.rs
+++ b/candle-transformers/src/models/t5.rs
@@ -14,6 +14,49 @@
//! - [T5 Paper](https://arxiv.org/abs/1910.10683)
//! - [HuggingFace T5](https://huggingface.co/docs/transformers/model_doc/t5)
//! - [GH Model](https://github.com/huggingface/transformers/blob/main/src/transformers/models/t5/modeling_t5.py)
+//!
+//! # Encoder-decoder example:
+//!
+//! ```bash
+//! cargo run --example t5 --release -- \
+//! --model-id "t5-small" \
+//! --prompt "translate to German: A beautiful candle." \
+//! --decode
+//! > ...
+//! > Eine schöne Kerze.
+//! > 9 tokens generated (2.42 token/s)
+//! ```
+//!
+//! Variants such as [flan-t5](https://huggingface.co/google/flan-t5-small), [flan-ul2](https://huggingface.co/google/flan-ul2) (with `--revision "refs/pr/25"`), and [Co-EdIT](https://huggingface.co/grammarly/coedit-large) are also supported.
+//!
+//! # Translation with MADLAD
+//!
+//!
+//! [MADLAD-400](https://arxiv.org/abs/2309.04662) is a series of multilingual machine translation T5 models trained on 250 billion tokens covering over 450 languages using publicly available data. These models are competitive with significantly larger models.
+//!
+//! ```bash
+//! cargo run --example t5 --release -- \
+//! --model-id "jbochi/madlad400-3b-mt" \
+//! --prompt "<2de> How are you, my friend?" \
+//! --decode --temperature 0
+//! ...
+//! Wie geht es dir, mein Freund?
+//! ```
+//!
+//! ## Sentence embedding example
+//!
+//! ```bash
+//! cargo run --example t5 --release -- \
+//! --model-id "t5-small" --prompt "A beautiful candle."
+//! ...
+//! [[[ 0.0515, -0.0541, -0.0761, ..., -0.0392, 0.1511, -0.0265],
+//! [-0.0974, 0.0998, -0.1659, ..., -0.2450, 0.1738, -0.0164],
+//! [ 0.0624, -0.1024, 0.0430, ..., -0.1388, 0.0564, -0.2962],
+//! [-0.0389, -0.1173, 0.0026, ..., 0.1064, -0.1065, 0.0990],
+//! [ 0.1300, 0.0027, -0.0326, ..., 0.0026, -0.0317, 0.0851]]]
+//! Tensor[[1, 5, 512], f32]
+//! Took 303.766583ms
+//! ```
use crate::models::with_tracing::Embedding;
use candle::{DType, Device, Module, Result, Tensor, D};