robo-lib 0.0.7__tar.gz → 0.0.9__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {robo_lib-0.0.7 → robo_lib-0.0.9}/PKG-INFO +4 -4
- {robo_lib-0.0.7 → robo_lib-0.0.9}/README.md +3 -3
- {robo_lib-0.0.7 → robo_lib-0.0.9}/pyproject.toml +1 -1
- {robo_lib-0.0.7 → robo_lib-0.0.9}/LICENSE +0 -0
- {robo_lib-0.0.7 → robo_lib-0.0.9}/robo_lib/__init__.py +0 -0
- {robo_lib-0.0.7 → robo_lib-0.0.9}/robo_lib/components.py +0 -0
- {robo_lib-0.0.7 → robo_lib-0.0.9}/tests/__init__.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.3
|
|
2
2
|
Name: robo_lib
|
|
3
|
-
Version: 0.0.
|
|
3
|
+
Version: 0.0.9
|
|
4
4
|
Summary: A package to create, configure, and train transformer models.
|
|
5
5
|
Project-URL: Homepage, https://github.com/hamburgerfish/robo_pack
|
|
6
6
|
Project-URL: Issues, https://github.com/hamburgerfish/robo_pack/issues
|
|
@@ -48,7 +48,7 @@ encoder_tok = rl.TokenizerConstructor(tokenizer_type="WordLevel")
|
|
|
48
48
|
encoder_tok.train("english_data.txt")
|
|
49
49
|
|
|
50
50
|
decoder_tok = rl.TokenizerConstructor(tokenizer_type="WordLevel")
|
|
51
|
-
|
|
51
|
+
decoder_tok.train("french_data.txt")
|
|
52
52
|
|
|
53
53
|
rl.save_component(encoder_tok, "tokenizers/encoder_tok.pkl")
|
|
54
54
|
rl.save_component(decoder_tok, "tokenizers/decoder_tok.pkl")
|
|
@@ -71,7 +71,7 @@ with open("french_data.txt", "r") as file:
|
|
|
71
71
|
|
|
72
72
|
# splitting lists into train and validation sets
|
|
73
73
|
split = 0.9
|
|
74
|
-
n = int(len(english_list) *
|
|
74
|
+
n = int(len(english_list) * split)
|
|
75
75
|
english_train = english_list[:n]
|
|
76
76
|
french_train = french_list[:n]
|
|
77
77
|
english_val = english_list[n:]
|
|
@@ -187,7 +187,7 @@ with open("shakespeare_dialogues.txt", "r") as file:
|
|
|
187
187
|
|
|
188
188
|
# splitting string into train and validation sets
|
|
189
189
|
split = 0.9
|
|
190
|
-
n = int(len(dialogues_str) *
|
|
190
|
+
n = int(len(dialogues_str) * split)
|
|
191
191
|
train_data = dialogues_str[:n]
|
|
192
192
|
val_data = dialogues_str[n:]
|
|
193
193
|
|
|
@@ -31,7 +31,7 @@ encoder_tok = rl.TokenizerConstructor(tokenizer_type="WordLevel")
|
|
|
31
31
|
encoder_tok.train("english_data.txt")
|
|
32
32
|
|
|
33
33
|
decoder_tok = rl.TokenizerConstructor(tokenizer_type="WordLevel")
|
|
34
|
-
|
|
34
|
+
decoder_tok.train("french_data.txt")
|
|
35
35
|
|
|
36
36
|
rl.save_component(encoder_tok, "tokenizers/encoder_tok.pkl")
|
|
37
37
|
rl.save_component(decoder_tok, "tokenizers/decoder_tok.pkl")
|
|
@@ -54,7 +54,7 @@ with open("french_data.txt", "r") as file:
|
|
|
54
54
|
|
|
55
55
|
# splitting lists into train and validation sets
|
|
56
56
|
split = 0.9
|
|
57
|
-
n = int(len(english_list) *
|
|
57
|
+
n = int(len(english_list) * split)
|
|
58
58
|
english_train = english_list[:n]
|
|
59
59
|
french_train = french_list[:n]
|
|
60
60
|
english_val = english_list[n:]
|
|
@@ -170,7 +170,7 @@ with open("shakespeare_dialogues.txt", "r") as file:
|
|
|
170
170
|
|
|
171
171
|
# splitting string into train and validation sets
|
|
172
172
|
split = 0.9
|
|
173
|
-
n = int(len(dialogues_str) *
|
|
173
|
+
n = int(len(dialogues_str) * split)
|
|
174
174
|
train_data = dialogues_str[:n]
|
|
175
175
|
val_data = dialogues_str[n:]
|
|
176
176
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|