From 9b3bf4a2065811c3845cd8d456f5b6f10b9906fa Mon Sep 17 00:00:00 2001
From: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
Date: Thu, 24 Apr 2025 11:10:27 +0200
Subject: [PATCH] Fix torchao doc examples (#37697)

fix

Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
---
 docs/source/en/quantization/torchao.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/docs/source/en/quantization/torchao.md b/docs/source/en/quantization/torchao.md
index f3153d9f22..42fed458f7 100644
--- a/docs/source/en/quantization/torchao.md
+++ b/docs/source/en/quantization/torchao.md
@@ -149,7 +149,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```py
 import torch
 from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-from torchao.quantization import Int8WeightOnlyConfig
+from torchao.quantization import Int8DynamicActivationInt8WeightConfig
 
 quant_config = Int8DynamicActivationInt8WeightConfig()
 # or int8 weight only quantization
@@ -179,7 +179,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```py
 import torch
 from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-from torchao.quantization import Int4WeightOnlyConfig
+from torchao.quantization import GemliteUIntXWeightOnlyConfig
 
 # For batch size N, we recommend gemlite, which may require autotuning
 # default is 4 bit, 8 bit is also supported by passing `bit_width=8`
@@ -216,7 +216,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```py
 import torch
 from transformers import TorchAoConfig, AutoModelForCausalLM, AutoTokenizer
-from torchao.quantization import Int8WeightOnlyConfig
+from torchao.quantization import Int8DynamicActivationInt8WeightConfig
 
 quant_config = Int8DynamicActivationInt8WeightConfig()
 # quant_config = Int8WeightOnlyConfig()