From 2e637be5d6b3e15c2b300130599bcec0f3e12ec8 Mon Sep 17 00:00:00 2001
From: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
Date: Fri, 25 Oct 2024 13:41:10 +0200
Subject: [PATCH] Add sentence-transformers and timm documentation example
 (#2072)

* add sentence-transformers and timm example to documentation

* replace with onnx models

* rephrase
---
 .../onnxruntime/usage_guides/models.mdx       | 58 ++++++++++++++++++-
 1 file changed, 56 insertions(+), 2 deletions(-)

diff --git a/docs/source/onnxruntime/usage_guides/models.mdx b/docs/source/onnxruntime/usage_guides/models.mdx
index 905e6632c05..27ac446096b 100644
--- a/docs/source/onnxruntime/usage_guides/models.mdx
+++ b/docs/source/onnxruntime/usage_guides/models.mdx
@@ -9,7 +9,7 @@ to run accelerated inference without rewriting your APIs.
 
 ### Transformers models
 
-Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing the `AutoModelForXxx` class with the corresponding `ORTModelForXxx`.
+Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing `AutoModelForXxx` with the corresponding `ORTModelForXxx` class.
 
 ```diff
   from transformers import AutoTokenizer, pipeline
@@ -29,7 +29,7 @@ More information for all the supported `ORTModelForXxx` in our [documentation](h
 
 ### Diffusers models
 
-Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing the `DiffusionPipeline` class with the corresponding `ORTDiffusionPipeline`.
+Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing `DiffusionPipeline` with the corresponding `ORTDiffusionPipeline` class.
 
 
 ```diff
@@ -43,6 +43,60 @@ Once your model was [exported to the ONNX format](https://huggingface.co/docs/op
   image = pipeline(prompt).images[0]
 ```
 
+
+### Sentence Transformers models
+
+Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing `AutoModel` with the corresponding `ORTModelForFeatureExtraction` class.
+
+```diff
+  from transformers import AutoTokenizer
+- from transformers import AutoModel
++ from optimum.onnxruntime import ORTModelForFeatureExtraction
+
+  tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
+- model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
++ model = ORTModelForFeatureExtraction.from_pretrained("optimum/all-MiniLM-L6-v2")
+  inputs = tokenizer("This is an example sentence", return_tensors="pt")
+  outputs = model(**inputs)
+```
+
+You can also load your ONNX model directly using the [`sentence_transformers.SentenceTransformer`](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#onnx) class, just make sure to have `sentence-transformers>=3.2` installed. If the model wasn't already converted to ONNX, it will be converted automatically on-the-fly.
+
+```diff
+  from sentence_transformers import SentenceTransformer
+
+  model_id = "sentence-transformers/all-MiniLM-L6-v2"
+- model = SentenceTransformer(model_id)
++ model = SentenceTransformer(model_id, backend="onnx")
+
+  sentences = ["This is an example sentence", "Each sentence is converted"]
+  embeddings = model.encode(sentences)
+```
+
+
+### Timm models
+
+Once your model was [exported to the ONNX format](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), you can load it by replacing the `create_model` with the corresponding `ORTModelForImageClassification` class.
+
+
+```diff
+  import requests
+  from PIL import Image
+- from timm import create_model
+  from timm.data import resolve_data_config, create_transform
++ from optimum.onnxruntime import ORTModelForImageClassification
+
+- model = create_model("timm/mobilenetv3_large_100.ra_in1k", pretrained=True)
++ model = ORTModelForImageClassification.from_pretrained("optimum/mobilenetv3_large_100.ra_in1k")
+  transform = create_transform(**resolve_data_config(model.config.pretrained_cfg, model=model))
+  url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png"
+  image = Image.open(requests.get(url, stream=True).raw)
+  inputs = transform(image).unsqueeze(0)
+  outputs = model(inputs)
+```
+
+
+
 ## Converting your model to ONNX on-the-fly
 
 In case your model wasn't already [converted to ONNX](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/export_a_model), [`~optimum.onnxruntime.ORTModel`] includes a method to convert your model to ONNX on-the-fly.