Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

fix typos (#185)

wenhuach2124b2e74070f2
diff --git a/README.md b/README.md
index f9b834fa0..186825bf2 100644
--- a/README.md
+++ b/README.md
@@ -128,7 +128,7 @@ autoround.save_quantized(output_dir) ##save_quantized(output_dir,format="auto_ro
### Tips
-1 Consider increasin 'iters' (e.g. 1000) to achieve better results, albeit with increased tuning time.
+1 Consider increasing 'iters' (e.g. 1000) to achieve better results, albeit with increased tuning time.
2 Consider increasing 'nsamples' (e.g. 512) to achieve better results, albeit with more memory(~20G).
diff --git a/examples/multimodal-modeling/Llava/main.py b/examples/multimodal-modeling/Llava/main.py
index 0018ea763..5dc734d2b 100644
--- a/examples/multimodal-modeling/Llava/main.py
+++ b/examples/multimodal-modeling/Llava/main.py
@@ -41,7 +41,7 @@ class CustomDataset(Dataset): # for llava tuning
image = Image.open(os.path.join(self.image_folder, image_file)).convert('RGB')
image = self.image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0]
except Exception as error:
- print(f"{error}, skiped by set image to None")
+ print(f"{error}, skipped by set image to None")
image = None
sources = preprocess_multimodal(
copy.deepcopy([sources["conversations"]]), # a list