From 0a0261740b29e01d6a571f2f5353a98d4e58bdaa Mon Sep 17 00:00:00 2001
From: Kenan Arslanbay <66200735+kenanarslanbay@users.noreply.github.com>
Date: Sat, 20 Apr 2024 14:27:44 +0200
Subject: [PATCH] Update README.md

Update roberta inference notebook url

Signed-off-by: Kenan Arslanbay <66200735+kenanarslanbay@users.noreply.github.com>
---
 validated/text/machine_comprehension/roberta/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/validated/text/machine_comprehension/roberta/README.md b/validated/text/machine_comprehension/roberta/README.md
index 83c3dfb3d..a7db95830 100644
--- a/validated/text/machine_comprehension/roberta/README.md
+++ b/validated/text/machine_comprehension/roberta/README.md
@@ -29,7 +29,7 @@ Official tool from HuggingFace that can be used to convert transformers models t
 ## Inference
 We used [ONNX Runtime](https://github.com/microsoft/onnxruntime) to perform the inference.
 
-Tutorial for running inference for RoBERTa-SequenceClassification model using onnxruntime can be found in the [inference](dependencies/roberta-inference.ipynb) notebook.
+Tutorial for running inference for RoBERTa-SequenceClassification model using onnxruntime can be found in the [inference](https://github.com/onnx/models/blob/main/validated/text/machine_comprehension/roberta/dependencies/roberta-sequence-classification-inference.ipynb) notebook.
 
 ### Input
 input_ids: Indices of input tokens in the vocabulary. It's a int64 tensor of dynamic shape (batch_size, sequence_length). Text tokenized by RobertaTokenizer.