rebase code on main branch

PenghuiCheng · PenghuiCheng · commit ecaac6e62a3c · 2024-01-16T18:58:34.000+08:00
Signed-off-by: Cheng, Penghui &lt;penghui.cheng@intel.com&gt;
diff --git a/examples/neural_compressor/language-modeling/README.md b/examples/neural_compressor/language-modeling/README.md
@@ -97,4 +97,4 @@ respectively `dynamic`, `static`, `weight_only` or `aware_training`.
 
 The flag `--verify_loading` can be passed along to verify that the resulting quantized model can be loaded correctly.
 
-> **_Note:_** `weight_only` quantization_approach requires neural-compressor >= 2.3 and intel-extension-for-transformers >= 1.2.
+> **_Note:_** `weight_only` quantization_approach requires neural-compressor >= 2.3 and intel-extension-for-transformers >= 1.3.
diff --git a/examples/neural_compressor/language-modeling/requirements.txt b/examples/neural_compressor/language-modeling/requirements.txt
@@ -3,5 +3,5 @@ torch >= 1.9
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-intel-extension-for-transformers
+intel-extension-for-transformers >=1.3
 peft
diff --git a/setup.py b/setup.py
@@ -32,7 +32,7 @@
     "rjieba",
     "timm",
     "invisible-watermark>=0.2.0",
-    "intel-extension-for-transformers",
+    "intel-extension-for-transformers>=1.3",
     "peft",
 ]
 

Original file line number	Diff line number	Diff line change
@@ -97,4 +97,4 @@ respectively `dynamic`, `static`, `weight_only` or `aware_training`.
`97`	`97`
`98`	`98`	The flag `--verify_loading` can be passed along to verify that the resulting quantized model can be loaded correctly.
`99`	`99`
`100`		-> _Note:_ `weight_only` quantization_approach requires neural-compressor >= 2.3 and intel-extension-for-transformers >= 1.2.
	`100`	+> _Note:_ `weight_only` quantization_approach requires neural-compressor >= 2.3 and intel-extension-for-transformers >= 1.3.
Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@`
`32`	`32`	`"rjieba",`
`33`	`33`	`"timm",`
`34`	`34`	`"invisible-watermark>=0.2.0",`
`35`		`- "intel-extension-for-transformers",`
	`35`	`+ "intel-extension-for-transformers>=1.3",`
`36`	`36`	`"peft",`
`37`	`37`	`]`
`38`	`38`