From 20494f6e11b246c269c35027f0182a182f264940 Mon Sep 17 00:00:00 2001
From: MelodicTechno <617179025@qq.com>
Date: Fri, 26 Jul 2024 22:48:15 +0800
Subject: [PATCH 1/3] Modify: enable UTF-8 encoding

---
 .../similarity-analogy_origin.md                                | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md b/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
index 93a6cd1f7..91449867e 100644
--- a/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
+++ b/chapter_natural-language-processing-pretraining/similarity-analogy_origin.md
@@ -81,7 +81,7 @@ class TokenEmbedding:
         data_dir = d2l.download_extract(embedding_name)
         # GloVe website: https://nlp.stanford.edu/projects/glove/
         # fastText website: https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r', encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]

From 7e285a9e63f8da92974469be1905ca8fac65c66b Mon Sep 17 00:00:00 2001
From: MelodicTechno <617179025@qq.com>
Date: Fri, 26 Jul 2024 23:10:56 +0800
Subject: [PATCH 2/3] Modify: enable UTF-8 encoding in mxnet & paddle

---
 d2l/mxnet.py      | 2 +-
 d2l/paddle.py     | 2 +-
 d2l/tensorflow.py | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/d2l/mxnet.py b/d2l/mxnet.py
index 25fc6eaf3..80e6af6d8 100644
--- a/d2l/mxnet.py
+++ b/d2l/mxnet.py
@@ -2071,7 +2071,7 @@ def _load_embedding(self, embedding_name):
         data_dir = d2l.download_extract(embedding_name)
         # GloVe网站：https://nlp.stanford.edu/projects/glove/
         # fastText网站：https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r', encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]
diff --git a/d2l/paddle.py b/d2l/paddle.py
index 6c5813aeb..fc03a9a8a 100644
--- a/d2l/paddle.py
+++ b/d2l/paddle.py
@@ -2201,7 +2201,7 @@ def _load_embedding(self, embedding_name):
         data_dir = d2l.download_extract(embedding_name)
         # GloVe网站：https://nlp.stanford.edu/projects/glove/
         # fastText网站：https://fasttext.cc/
-        with open(os.path.join(data_dir, 'vec.txt'), 'r') as f:
+        with open(os.path.join(data_dir, 'vec.txt'), 'r' , encoding='utf-8') as f:
             for line in f:
                 elems = line.rstrip().split(' ')
                 token, elems = elems[0], [float(elem) for elem in elems[1:]]
diff --git a/d2l/tensorflow.py b/d2l/tensorflow.py
index 85705dceb..7b8895388 100644
--- a/d2l/tensorflow.py
+++ b/d2l/tensorflow.py
@@ -1,4 +1,4 @@
-DATA_HUB = dict()
+gitDATA_HUB = dict()
 DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'
 
 import numpy as np

From 53da05a4bcc8d8cfea5432a4c9b5e4ad3c07ce33 Mon Sep 17 00:00:00 2001
From: MelodicTechno <617179025@qq.com>
Date: Fri, 26 Jul 2024 23:13:12 +0800
Subject: [PATCH 3/3] delete the 'git' that added accidentally

---
 d2l/tensorflow.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/d2l/tensorflow.py b/d2l/tensorflow.py
index 7b8895388..85705dceb 100644
--- a/d2l/tensorflow.py
+++ b/d2l/tensorflow.py
@@ -1,4 +1,4 @@
-gitDATA_HUB = dict()
+DATA_HUB = dict()
 DATA_URL = 'http://d2l-data.s3-accelerate.amazonaws.com/'
 
 import numpy as np