From dda2ccacb59577df345b7bd557c93d98b4b3784a Mon Sep 17 00:00:00 2001
From: changwangss <chang1.wang@intel.com>
Date: Wed, 18 Oct 2023 14:08:47 -0700
Subject: [PATCH 1/5] reduce the evaluation time

Signed-off-by: changwangss <chang1.wang@intel.com>
---
 tests/test_evaluation.py | 78 ++++++++++++++--------------------------
 1 file changed, 26 insertions(+), 52 deletions(-)

diff --git a/tests/test_evaluation.py b/tests/test_evaluation.py
index 8a3fd557275..97c74864748 100644
--- a/tests/test_evaluation.py
+++ b/tests/test_evaluation.py
@@ -10,10 +10,9 @@ class TestLmEvaluationHarness(unittest.TestCase):
     @classmethod
     def setUpClass(self):
         self.clm_model = AutoModelForCausalLM.from_pretrained(
-            "facebook/opt-125m",
+            "hf-internal-testing/tiny-random-gptj",
             torchscript=True
         )
-        self.seq2seq_model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
         tmp_model = torch.jit.trace(
             self.clm_model, self.clm_model.dummy_inputs["input_ids"]
         )
@@ -33,22 +32,21 @@ def tearDownClass(self):
         shutil.rmtree("./gptj", ignore_errors=True)
         shutil.rmtree("./gptj-past", ignore_errors=True)
         shutil.rmtree("./evaluation_results.json", ignore_errors=True)
-        shutil.rmtree("./llama", ignore_errors=True)
         cmd = 'pip uninstall lm_eval -y'
         p = subprocess.Popen(cmd, preexec_fn=os.setsid, stdout=subprocess.PIPE,
                                              stderr=subprocess.PIPE, shell=True) # nosec
         p.communicate()
 
 
-    def test_evaluate_for_casualLM(self):
+    def test_evaluate_for_CasualLM(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
         results = evaluate(
             model="hf-causal",
             model_args='pretrained="hf-internal-testing/tiny-random-gptj",tokenizer="hf-internal-testing/tiny-random-gptj",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.45)
+        self.assertEqual(results["results"]["piqa"]["acc"], 0.6)
 
     def test_evaluate_for_Seq2SeqLM(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
@@ -56,9 +54,9 @@ def test_evaluate_for_Seq2SeqLM(self):
             model="hf-seq2seq",
             model_args='pretrained="hf-internal-testing/tiny-random-t5",tokenizer="hf-internal-testing/tiny-random-t5",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.60)
+        self.assertEqual(results["results"]["piqa"]["acc"], 1.0)
 
     def test_evaluate_for_JitModel(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
@@ -67,34 +65,26 @@ def test_evaluate_for_JitModel(self):
             model_args='pretrained="hf-internal-testing/tiny-random-gptj",tokenizer="hf-internal-testing/tiny-random-gptj",dtype=float32',
             user_model=self.jit_model,
             tasks=["piqa"],
-            limit=20,
+            limit=5,
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.65)
+        self.assertEqual(results["results"]["piqa"]["acc"], 0.6)
 
-    def test_lambada_for_llama(self):
-        from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
-        results = evaluate(
-            model="hf-causal",
-            model_args='pretrained="decapoda-research/llama-7b-hf",tokenizer="decapoda-research/llama-7b-hf",dtype=float32',
-            tasks=["lambada_openai", "lambada_standard"],
-            limit=20,
-        )
-        self.assertEqual(results["results"]["lambada_standard"]["acc"], 0.75)
-        self.assertEqual(results["results"]["lambada_openai"]["acc"], 0.70)
 
     def test_cnn_daily(self):
         from intel_extension_for_transformers.llm.evaluation.hf_eval import summarization_evaluate
+        model = AutoModelForCausalLM.from_pretrained("facebook/opt-125m")
         results = summarization_evaluate(
-           model=self.clm_model,
+           model=model,
            tokenizer_name="facebook/opt-125m",
            batch_size=1,
            limit=5,
         )
         self.assertEqual(results["rouge2"], 18.0431)
+        model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
         results = summarization_evaluate(
-            model=self.seq2seq_model, tokenizer_name="t5-small", batch_size=1, limit=5
+            model=model, tokenizer_name="t5-small", batch_size=1, limit=5
         )
-        self.assertEqual(results["rouge2"], 9.6795)
+        self.assertEqual(results["rouge2"], 9.5858)
     
     def test_evaluate_for_ort_Seq2SeqLM(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
@@ -108,10 +98,10 @@ def test_evaluate_for_ort_Seq2SeqLM(self):
             model="hf-seq2seq",
             model_args='pretrained="./t5-past",tokenizer="./t5-past",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
             model_format="onnx"
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.60)
+        self.assertEqual(results["results"]["piqa"]["acc"], 1.0)
 
         # test evaluate encoder_model + decoder_model + decoder_with_past_model
         merged_model_path = "./t5-past/decoder_model_merged.onnx"
@@ -121,10 +111,10 @@ def test_evaluate_for_ort_Seq2SeqLM(self):
                 model="hf-seq2seq",
                 model_args='pretrained="./t5-past",tokenizer="./t5-past",dtype=float32',
                 tasks=["piqa"],
-                limit=20,
+                limit=5,
                 model_format="onnx"
             )
-            self.assertEqual(results["results"]["piqa"]["acc"], 0.60)
+            self.assertEqual(results["results"]["piqa"]["acc"], 1.0)
 
         # test evaluate encoder_model + decoder_model
         cmd = 'optimum-cli export onnx --model hf-internal-testing/tiny-random-t5 --task text2text-generation t5/'
@@ -135,12 +125,12 @@ def test_evaluate_for_ort_Seq2SeqLM(self):
             model="hf-seq2seq",
             model_args='pretrained="./t5",tokenizer="./t5",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
             model_format="onnx"
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.60)
+        self.assertEqual(results["results"]["piqa"]["acc"], 1.0)
 
-    def test_evaluate_for_ort_casualLM(self):
+    def test_evaluate_for_ort_CasualLM(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
         cmd = 'optimum-cli export onnx --model hf-internal-testing/tiny-random-gptj --task text-generation-with-past gptj-past/'
         p = subprocess.Popen(cmd, preexec_fn=os.setsid, stdout=subprocess.PIPE,
@@ -152,10 +142,10 @@ def test_evaluate_for_ort_casualLM(self):
             model="hf-causal",
             model_args='pretrained="./gptj-past",tokenizer="./gptj-past",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
             model_format="onnx"
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.45)
+        self.assertEqual(results["results"]["piqa"]["acc"], 0.6)
 
         # test evaluate decoder_model + decoder_with_past_model
         merged_model_path = "./gptj-past/decoder_model_merged.onnx"
@@ -165,10 +155,10 @@ def test_evaluate_for_ort_casualLM(self):
                 model="hf-causal",
                 model_args='pretrained="./gptj-past",tokenizer="./gptj-past",dtype=float32',
                 tasks=["piqa"],
-                limit=20,
+                limit=5,
                 model_format="onnx"
             )
-            self.assertEqual(results["results"]["piqa"]["acc"], 0.45)
+            self.assertEqual(results["results"]["piqa"]["acc"], 0.6)
 
         # test evaluate decoder_model
         cmd = 'optimum-cli export onnx --model hf-internal-testing/tiny-random-gptj --task text-generation gptj/'
@@ -179,27 +169,11 @@ def test_evaluate_for_ort_casualLM(self):
             model="hf-causal",
             model_args='pretrained="./gptj",tokenizer="./gptj",dtype=float32',
             tasks=["piqa"],
-            limit=20,
+            limit=5,
             model_format="onnx"
         )
-        self.assertEqual(results["results"]["piqa"]["acc"], 0.45)
+        self.assertEqual(results["results"]["piqa"]["acc"], 0.6)
 
 
-    def test_tokenizer_for_llama(self):
-        from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate
-        cmd = 'optimum-cli export onnx --model decapoda-research/llama-7b-hf --task text-generation llama/'
-        p = subprocess.Popen(cmd, preexec_fn=os.setsid, stdout=subprocess.PIPE,
-                                            stderr=subprocess.PIPE, shell=True) # nosec
-        p.communicate()
-
-        results = evaluate(
-            model="hf-causal",
-            model_args='pretrained="./llama",tokenizer="decapoda-research/llama-7b-hf"',
-            tasks=["lambada_openai"],
-            limit=20,
-            model_format="onnx"
-        )
-        self.assertEqual(results["results"]["lambada_openai"]["acc"], 0.70)
-
 if __name__ == "__main__":
     unittest.main()

From 4adacf1112d9fd88a83c5cc7bcf7f3734e48ffec Mon Sep 17 00:00:00 2001
From: Wenxin Zhang <wenxin.zhang@intel.com>
Date: Thu, 19 Oct 2023 13:55:29 +0800
Subject: [PATCH 2/5] use INC 2.3.1

Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
---
 .../workflows/script/unitTest/env_setup.sh    | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/.github/workflows/script/unitTest/env_setup.sh b/.github/workflows/script/unitTest/env_setup.sh
index 47ca0650e3d..969c1c75e0c 100644
--- a/.github/workflows/script/unitTest/env_setup.sh
+++ b/.github/workflows/script/unitTest/env_setup.sh
@@ -7,15 +7,16 @@ if [ ${inc} != 0 ]; then
 fi
 
 echo "Install neural_compressor binary..."
-n=0
-until [ "$n" -ge 5 ]; do
-    git clone https://github.com/intel/neural-compressor.git /neural-compressor
-    cd /neural-compressor
-    pip install -r requirements.txt
-    python setup.py install && break
-    n=$((n + 1))
-    sleep 5
-done
+pip install neural-compressor
+#n=0
+#until [ "$n" -ge 5 ]; do
+#    git clone https://github.com/intel/neural-compressor.git /neural-compressor
+#    cd /neural-compressor
+#    pip install -r requirements.txt
+#    python setup.py install && break
+#    n=$((n + 1))
+#    sleep 5
+#done
 
 # Install test requirements
 cd /intel-extension-for-transformers/tests

From 0487248d32468c76f46f768ce6e3984b1865c108 Mon Sep 17 00:00:00 2001
From: "Wang, Chang" <chang1.wang@intel.com>
Date: Thu, 19 Oct 2023 17:41:10 +0800
Subject: [PATCH 3/5] Update test_evaluation.py

Signed-off-by: Wang, Chang <chang1.wang@intel.com>
---
 tests/test_evaluation.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_evaluation.py b/tests/test_evaluation.py
index 97c74864748..e42e5d96aad 100644
--- a/tests/test_evaluation.py
+++ b/tests/test_evaluation.py
@@ -84,7 +84,7 @@ def test_cnn_daily(self):
         results = summarization_evaluate(
             model=model, tokenizer_name="t5-small", batch_size=1, limit=5
         )
-        self.assertEqual(results["rouge2"], 9.5858)
+        self.assertEqual(results["rouge2"], 9.6795)
     
     def test_evaluate_for_ort_Seq2SeqLM(self):
         from intel_extension_for_transformers.llm.evaluation.lm_eval import evaluate

From e83812feb7ffe0cce86cf6acb61356b179650240 Mon Sep 17 00:00:00 2001
From: Wenxin Zhang <wenxin.zhang@intel.com>
Date: Thu, 19 Oct 2023 17:52:56 +0800
Subject: [PATCH 4/5] update torch/ipex version

Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
---
 .../deployment/imagenet/vit/requirements.txt              | 2 +-
 .../image-classification/quantization/requirements.txt    | 2 +-
 .../fill-mask/electra_base_chinese/requirements.txt       | 2 +-
 .../deployment/squad/bert_large/requirements.txt          | 2 +-
 .../squad/length_adaptive_transformer/requirements.txt    | 2 +-
 .../pytorch/question-answering/dynamic/requirements.txt   | 2 +-
 .../pruning/basic_magnitude/requirements.txt              | 2 +-
 .../pruning/longformer_triviaqa/requirements.txt          | 2 +-
 .../pytorch/summarization/quantization/requirements.txt   | 2 +-
 .../text-classification/cascade-models/requirements.txt   | 2 +-
 .../emotion/distilbert_base_uncased/requirements.txt      | 2 +-
 .../deployment/mrpc/bert_base/requirements.txt            | 2 +-
 .../deployment/mrpc/bert_base_cased/requirements.txt      | 2 +-
 .../deployment/mrpc/bert_mini/requirements.txt            | 2 +-
 .../mrpc/distilbert_base_uncased/requirements.txt         | 2 +-
 .../deployment/mrpc/roberta_base/requirements.txt         | 2 +-
 .../deployment/sparse/bert_mini/requirements.txt          | 2 +-
 .../sparse/distilbert_base_uncased/requirements.txt       | 2 +-
 .../deployment/sst2/bert_mini/requirements.txt            | 2 +-
 .../sst2/distilbert_base_uncased/requirements.txt         | 2 +-
 .../sst2/minilm_l6_h384_uncased/requirements.txt          | 2 +-
 .../text-classification/early-exit/requirements.txt       | 2 +-
 .../text-classification/new_pruning/requirements.txt      | 2 +-
 .../orchestrate_optimizations/requirements.txt            | 2 +-
 .../pytorch/text-classification/pruning/requirements.txt  | 2 +-
 .../text-classification/quantization/ptq/requirements.txt | 2 +-
 .../text-classification/quantization/qat/requirements.txt | 2 +-
 .../text-classification/quantization/requirements.txt     | 2 +-
 .../deployment/stable_diffusion/requirements.txt          | 2 +-
 .../textual-inversion/quantization/requirements.txt       | 2 +-
 .../token-classification/quantization/requirements.txt    | 2 +-
 .../pytorch/translation/quantization/requirements.txt     | 2 +-
 .../neural_chat/docker/Dockerfile                         | 8 ++++----
 .../neural_chat/docker/finetuning/Dockerfile              | 2 +-
 .../docs/notebooks/multi_node_finetuning_on_spr.ipynb     | 2 +-
 .../neural_chat/examples/instruction_tuning/README.md     | 2 +-
 .../examples/instruction_tuning/requirements.txt          | 2 +-
 .../neural_chat/requirements.txt                          | 4 ++--
 .../neural_chat/requirements_cpu.txt                      | 6 +++---
 .../neural_chat/requirements_pc.txt                       | 4 ++--
 .../neural_chat/tests/requirements.txt                    | 4 ++--
 .../neural_chat/ui/textbot/requirements.txt               | 2 +-
 requirements.txt                                          | 2 +-
 tests/requirements.txt                                    | 2 +-
 workflows/chatbot/fine_tuning/README.md                   | 2 +-
 .../hf_finetuning_and_inference_nlp/requirements.txt      | 2 +-
 46 files changed, 54 insertions(+), 54 deletions(-)

diff --git a/examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt b/examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt
index 0efa4714cac..76366c5efbc 100644
--- a/examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt
+++ b/examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 torchvision
 onnx>=1.12
 onnxruntime==1.13.1
diff --git a/examples/huggingface/pytorch/image-classification/quantization/requirements.txt b/examples/huggingface/pytorch/image-classification/quantization/requirements.txt
index 517029af1af..d59aa71865a 100644
--- a/examples/huggingface/pytorch/image-classification/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/image-classification/quantization/requirements.txt
@@ -3,7 +3,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 torchvision
 onnx>=1.12
 onnxruntime==1.13.1
diff --git a/examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt b/examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt
index 75453d454e3..1a7cebc506e 100644
--- a/examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt
+++ b/examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt
@@ -1,2 +1,2 @@
 transformers
-torch==2.0.1
\ No newline at end of file
+torch==2.1.0
\ No newline at end of file
diff --git a/examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt b/examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt
+++ b/examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt b/examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt
index d78b3f5e411..e5d78e27646 100644
--- a/examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt
+++ b/examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.12.1
 
diff --git a/examples/huggingface/pytorch/question-answering/dynamic/requirements.txt b/examples/huggingface/pytorch/question-answering/dynamic/requirements.txt
index 8f7d7b7763a..b07abba0c1c 100644
--- a/examples/huggingface/pytorch/question-answering/dynamic/requirements.txt
+++ b/examples/huggingface/pytorch/question-answering/dynamic/requirements.txt
@@ -1,6 +1,6 @@
 transformers
 datasets
 torchprofile
-torch==2.0.1
+torch==2.1.0
 intel_extension_for_pytorch
 accelerate
diff --git a/examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt b/examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt
index adf0950d7e8..356d1691b68 100644
--- a/examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt
+++ b/examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt
@@ -1,5 +1,5 @@
 datasets >= 1.8.0
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
 accelerate
diff --git a/examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt b/examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt
index 6303484dd95..5a6251b32c9 100644
--- a/examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt
+++ b/examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt
@@ -1,5 +1,5 @@
 accelerate
 datasets
 transformers
-torch==2.0.1
+torch==2.1.0
 neural-compressor==2.0
diff --git a/examples/huggingface/pytorch/summarization/quantization/requirements.txt b/examples/huggingface/pytorch/summarization/quantization/requirements.txt
index 3196cace86f..cac876a61ee 100644
--- a/examples/huggingface/pytorch/summarization/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/summarization/quantization/requirements.txt
@@ -4,6 +4,6 @@ sentencepiece != 0.1.92
 rouge-score
 nltk
 py7zr
-torch==2.0.1
+torch==2.1.0
 transformers
 protobuf
diff --git a/examples/huggingface/pytorch/text-classification/cascade-models/requirements.txt b/examples/huggingface/pytorch/text-classification/cascade-models/requirements.txt
index 97c77505a07..04e5d00da95 100644
--- a/examples/huggingface/pytorch/text-classification/cascade-models/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/cascade-models/requirements.txt
@@ -1,4 +1,4 @@
-torch==2.0.1
+torch==2.1.0
 numpy
 transformers
 datasets
diff --git a/examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt b/examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt
index 273d45fd971..7661f639bc8 100644
--- a/examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 
diff --git a/examples/huggingface/pytorch/text-classification/early-exit/requirements.txt b/examples/huggingface/pytorch/text-classification/early-exit/requirements.txt
index 22c8a2d2cdd..dbc84748da8 100644
--- a/examples/huggingface/pytorch/text-classification/early-exit/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/early-exit/requirements.txt
@@ -1,4 +1,4 @@
-torch==2.0.1
+torch==2.1.0
 transformers
 datasets
 allennlp
diff --git a/examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt b/examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt
index d1684b2889f..57368f3c958 100644
--- a/examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt
@@ -6,5 +6,5 @@ sentencepiece
 scipy
 scikit-learn
 protobuf
-torch==2.0.1
+torch==2.1.0
 evaluate
\ No newline at end of file
diff --git a/examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt b/examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt
index b1b8aebabf1..60f12cca57c 100644
--- a/examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt
@@ -1,5 +1,5 @@
 accelerate
-torch==2.0.1
+torch==2.1.0
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 transformers
diff --git a/examples/huggingface/pytorch/text-classification/pruning/requirements.txt b/examples/huggingface/pytorch/text-classification/pruning/requirements.txt
index 6540152daf9..1456f81b2f3 100644
--- a/examples/huggingface/pytorch/text-classification/pruning/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/pruning/requirements.txt
@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
diff --git a/examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt b/examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt
index 6540152daf9..1456f81b2f3 100644
--- a/examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt
@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
diff --git a/examples/huggingface/pytorch/text-classification/quantization/qat/requirements.txt b/examples/huggingface/pytorch/text-classification/quantization/qat/requirements.txt
index 6540152daf9..1456f81b2f3 100644
--- a/examples/huggingface/pytorch/text-classification/quantization/qat/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/quantization/qat/requirements.txt
@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
diff --git a/examples/huggingface/pytorch/text-classification/quantization/requirements.txt b/examples/huggingface/pytorch/text-classification/quantization/requirements.txt
index 6540152daf9..1456f81b2f3 100644
--- a/examples/huggingface/pytorch/text-classification/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/text-classification/quantization/requirements.txt
@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
diff --git a/examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt b/examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt
index 52f0759c2ab..c74efb403bf 100644
--- a/examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt
+++ b/examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt
@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.0.1
+torch==2.1.0
 onnx>=1.12
 onnxruntime==1.13.1
 diffusers==0.12.1
diff --git a/examples/huggingface/pytorch/textual-inversion/quantization/requirements.txt b/examples/huggingface/pytorch/textual-inversion/quantization/requirements.txt
index 5b738372901..67a89afb643 100644
--- a/examples/huggingface/pytorch/textual-inversion/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/textual-inversion/quantization/requirements.txt
@@ -1,6 +1,6 @@
 diffusers==0.4.1
 accelerate
-torch==2.0.1
+torch==2.1.0
 torchvision
 transformers
 ftfy
diff --git a/examples/huggingface/pytorch/token-classification/quantization/requirements.txt b/examples/huggingface/pytorch/token-classification/quantization/requirements.txt
index 0403c13ac3b..50591581b25 100644
--- a/examples/huggingface/pytorch/token-classification/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/token-classification/quantization/requirements.txt
@@ -1,6 +1,6 @@
 accelerate
 seqeval
 datasets >= 1.1.3
-torch==2.0.1
+torch==2.1.0
 transformers
 wandb
diff --git a/examples/huggingface/pytorch/translation/quantization/requirements.txt b/examples/huggingface/pytorch/translation/quantization/requirements.txt
index 069db64bd79..436b3bcc059 100644
--- a/examples/huggingface/pytorch/translation/quantization/requirements.txt
+++ b/examples/huggingface/pytorch/translation/quantization/requirements.txt
@@ -4,5 +4,5 @@ sentencepiece != 0.1.92
 protobuf
 sacrebleu >= 1.4.12
 py7zr
-torch==2.0.1
+torch==2.1.0
 transformers
diff --git a/intel_extension_for_transformers/neural_chat/docker/Dockerfile b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
index 09ab00f65dc..93ce0fe9b52 100644
--- a/intel_extension_for_transformers/neural_chat/docker/Dockerfile
+++ b/intel_extension_for_transformers/neural_chat/docker/Dockerfile
@@ -66,11 +66,11 @@ RUN conda init bash && \
 
 ## If local torch whl are feasible, use localfile to install, avoiding donwloading time
 COPY ./torch*.whl /
-RUN if [ -f /torch-2.0.1+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torch-2.0.1+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
-RUN if [ -f /torchaudio-2.0.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchaudio-2.0.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
-RUN if [ -f /torchvision-0.15.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchvision-0.15.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
+RUN if [ -f /torch-2.1.0+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torch-2.0.1+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
+RUN if [ -f /torchaudio-2.1.0+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchaudio-2.0.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
+RUN if [ -f /torchvision-0.16.0+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl ]; then source activate && conda activate neuralchat && pip install /torchvision-0.15.2+cpu-cp3${PYTHON_VERSION##*.}-cp3${PYTHON_VERSION##*.}-linux_x86_64.whl; fi
 
-RUN source activate && conda activate neuralchat && pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
+RUN source activate && conda activate neuralchat && pip install oneccl_bind_pt==2.1.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
     cd /intel-extension-for-transformers && pip install -r requirements.txt && pip install -v . && \
     cd ./intel_extension_for_transformers/neural_chat/examples/instruction_tuning && pip install -r requirements.txt && \
     cd /intel-extension-for-transformers/intel_extension_for_transformers/neural_chat && pip install -r requirements_cpu.txt && \
diff --git a/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile b/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
index bd33a2f9fd3..ade85a371f9 100644
--- a/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
+++ b/intel_extension_for_transformers/neural_chat/docker/finetuning/Dockerfile
@@ -63,7 +63,7 @@ RUN conda init bash && \
     echo "conda activate chatbot-finetuning" >> ~/.bashrc && \
     source ~/.bashrc
 
-RUN source activate && conda activate chatbot-finetuning && pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
+RUN source activate && conda activate chatbot-finetuning && pip install oneccl_bind_pt==2.1.0 -f https://developer.intel.com/ipex-whl-stable-cpu && \
     pip install datasets torch accelerate SentencePiece evaluate nltk rouge_score protobuf==3.20.1 tokenizers einops && \
     git clone https://github.com/huggingface/peft.git && cd peft && python setup.py install && \
     cd /itrex && pip install -v . && \
diff --git a/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb b/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
index 788f9145d89..24971ab642c 100644
--- a/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
+++ b/intel_extension_for_transformers/neural_chat/docs/notebooks/multi_node_finetuning_on_spr.ipynb
@@ -23,7 +23,7 @@
     "```bash\n",
     "pip install -r requirements.txt\n",
     "# To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.\n",
-    "python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu\n",
+    "python -m pip install oneccl_bind_pt==2.1.0 -f https://developer.intel.com/ipex-whl-stable-cpu\n",
     "```\n",
     "\n",
     "Then, follow the [hugginface guide](https://huggingface.co/docs/transformers/perf_train_cpu_many) to install Intel® oneCCL Bindings for PyTorch, IPEX\n",
diff --git a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
index d25f15b1a38..200c39843e5 100644
--- a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
+++ b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/README.md
@@ -18,7 +18,7 @@ Recommend python 3.9 or higher version.
 ```shell
 pip install -r requirements.txt
 # To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.
-python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu
+python -m pip install oneccl_bind_pt==2.1.0 -f https://developer.intel.com/ipex-whl-stable-cpu
 ```
 
 ## 2. Prepare the Model
diff --git a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/requirements.txt b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/requirements.txt
index 6dbdb1ab8bd..4af5e860246 100644
--- a/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/requirements.txt
+++ b/intel_extension_for_transformers/neural_chat/examples/instruction_tuning/requirements.txt
@@ -1,5 +1,5 @@
 datasets
-torch==2.0.1
+torch==2.1.0
 transformers>=4.32.0
 sentencepiece
 peft
diff --git a/intel_extension_for_transformers/neural_chat/requirements.txt b/intel_extension_for_transformers/neural_chat/requirements.txt
index 0651e6ee2d0..86ebb418392 100644
--- a/intel_extension_for_transformers/neural_chat/requirements.txt
+++ b/intel_extension_for_transformers/neural_chat/requirements.txt
@@ -1,8 +1,8 @@
 transformers>=4.32.0
 peft
 fschat
-torch==2.0.1
-torchaudio==2.0.2
+torch==2.1.0
+torchaudio==2.1.0
 intel_extension_for_pytorch
 num2words
 speechbrain
diff --git a/intel_extension_for_transformers/neural_chat/requirements_cpu.txt b/intel_extension_for_transformers/neural_chat/requirements_cpu.txt
index 4ddfa0a21a0..90e21457a08 100644
--- a/intel_extension_for_transformers/neural_chat/requirements_cpu.txt
+++ b/intel_extension_for_transformers/neural_chat/requirements_cpu.txt
@@ -1,7 +1,7 @@
 transformers>=4.32.0
 peft
 fschat
-intel_extension_for_pytorch==2.0.100
+intel_extension_for_pytorch==2.1.0
 num2words
 speechbrain
 paddlepaddle
@@ -37,7 +37,7 @@ tiktoken==0.4.0
 lm_eval
 transformers_stream_generator==0.0.4
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.0.1
-torchaudio==2.0.2
+torch==2.1.0
+torchaudio==2.1.0
 spacy
 neural-compressor
\ No newline at end of file
diff --git a/intel_extension_for_transformers/neural_chat/requirements_pc.txt b/intel_extension_for_transformers/neural_chat/requirements_pc.txt
index dfe67fb69bd..4d2e292401c 100644
--- a/intel_extension_for_transformers/neural_chat/requirements_pc.txt
+++ b/intel_extension_for_transformers/neural_chat/requirements_pc.txt
@@ -35,7 +35,7 @@ numpy==1.23.5
 tiktoken==0.4.0
 lm_eval
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.0.1
-torchaudio==2.0.2
+torch==2.1.0
+torchaudio==2.1.0
 spacy
 neural-compressor
\ No newline at end of file
diff --git a/intel_extension_for_transformers/neural_chat/tests/requirements.txt b/intel_extension_for_transformers/neural_chat/tests/requirements.txt
index 096d9d93647..861d1469ab4 100644
--- a/intel_extension_for_transformers/neural_chat/tests/requirements.txt
+++ b/intel_extension_for_transformers/neural_chat/tests/requirements.txt
@@ -1,8 +1,8 @@
 transformers>=4.32.0
 peft
 fschat
-torch==2.0.1
-torchaudio==2.0.2
+torch==2.1.0
+torchaudio==2.1.0
 intel_extension_for_pytorch
 num2words
 speechbrain
diff --git a/intel_extension_for_transformers/neural_chat/ui/textbot/requirements.txt b/intel_extension_for_transformers/neural_chat/ui/textbot/requirements.txt
index e7c835c0e87..49e4e87b9c4 100644
--- a/intel_extension_for_transformers/neural_chat/ui/textbot/requirements.txt
+++ b/intel_extension_for_transformers/neural_chat/ui/textbot/requirements.txt
@@ -1,5 +1,5 @@
 pip
-torch==2.0.1
+torch==2.1.0
 diffusers==0.8.1
 transformers
 requests
diff --git a/requirements.txt b/requirements.txt
index 13d24a2bac6..b2b10389d7e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,5 +4,5 @@ py-cpuinfo
 setuptools>=65
 setuptools_scm[toml]>=6.2
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.0.1+cpu
+torch==2.1.0+cpu
 accelerate
diff --git a/tests/requirements.txt b/tests/requirements.txt
index 65577165dbd..bc416259e3f 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -6,7 +6,7 @@ neural-compressor
 onnx>=1.10
 onnxruntime
 --find-links https://download.pytorch.org/cpu/whl/torch_stable.html
-torch==2.0.1
+torch==2.1.0
 transformers
 intel-tensorflow==2.12.0
 torchprofile
diff --git a/workflows/chatbot/fine_tuning/README.md b/workflows/chatbot/fine_tuning/README.md
index 6bd52568499..28980dbbb6b 100644
--- a/workflows/chatbot/fine_tuning/README.md
+++ b/workflows/chatbot/fine_tuning/README.md
@@ -18,7 +18,7 @@ Recommend python 3.9 or higher version.
 ```shell
 pip install -r requirements.txt
 # To use ccl as the distributed backend in distributed training on CPU requires to install below requirement.
-python -m pip install oneccl_bind_pt==2.0.0 -f https://developer.intel.com/ipex-whl-stable-cpu
+python -m pip install oneccl_bind_pt==2.1.0 -f https://developer.intel.com/ipex-whl-stable-cpu
 ```
 
 ## 2. Prepare the Model
diff --git a/workflows/hf_finetuning_and_inference_nlp/requirements.txt b/workflows/hf_finetuning_and_inference_nlp/requirements.txt
index 38a57af4ae8..0221c42098d 100644
--- a/workflows/hf_finetuning_and_inference_nlp/requirements.txt
+++ b/workflows/hf_finetuning_and_inference_nlp/requirements.txt
@@ -2,7 +2,7 @@ transformers==4.31.0
 datasets==2.11.0
 neural-compressor==2.1
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.0.1
+torch==2.1.0
 intel_extension_for_pytorch==1.13.100
 intel-extension-for-transformers==1.0.0
 accelerate==0.21.0
\ No newline at end of file

From 5993a27eeff33230e34a41ead1765ec3ddfb164a Mon Sep 17 00:00:00 2001
From: Wenxin Zhang <wenxin.zhang@intel.com>
Date: Thu, 19 Oct 2023 18:03:27 +0800
Subject: [PATCH 5/5] run PR test only

Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
---
 .github/workflows/unit-test-neuralchat.yml | 4 ++--
 .github/workflows/unit-test-optimize.yml   | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/unit-test-neuralchat.yml b/.github/workflows/unit-test-neuralchat.yml
index 63956e2f903..a5f51315c2a 100644
--- a/.github/workflows/unit-test-neuralchat.yml
+++ b/.github/workflows/unit-test-neuralchat.yml
@@ -36,8 +36,8 @@ jobs:
         include:
           - test_branch: ${{ github.ref }}
             test_name: "PR-test"
-          - test_branch: "main"
-            test_name: "baseline"
+          #- test_branch: "main"
+          #  test_name: "baseline"
     steps:
       - name: podman Clean Up
         run: |
diff --git a/.github/workflows/unit-test-optimize.yml b/.github/workflows/unit-test-optimize.yml
index cee522c0819..bc7b3eff4e2 100644
--- a/.github/workflows/unit-test-optimize.yml
+++ b/.github/workflows/unit-test-optimize.yml
@@ -34,8 +34,8 @@ jobs:
         include:
           - test_branch: ${{ github.ref }}
             test_name: "PR-test"
-          - test_branch: "main"
-            test_name: "baseline"
+          #- test_branch: "main"
+          #  test_name: "baseline"
     steps:
       - name: Docker Clean Up
         run: |