yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-28 18:40:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

More pythonic way to find the longest sequence (#512)

Browse Source 
* More pythonic way to find the longest sequence

* pep8 fix
This commit is contained in:
Sebastian Raschka 2025-02-01 10:22:47 -06:00 committed by GitHub
parent c1c10c89c8
commit 7e2092dd01
5 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
appendix-E/01_main-chapter-code/previous_chapters.py
View File

@ -451,6 +451,9 @@ class SpamDataset(Dataset):
if encoded_length > max_length: if encoded_length > max_length:
max_length = encoded_length max_length = encoded_length
return max_length return max_length
# Note: A more pythonic version to implement this method
# is the following, which is also used in the next chapter:
# return max(len(encoded_text) for encoded_text in self.encoded_texts)
@torch.no_grad() # Disable gradient tracking for efficiency @torch.no_grad() # Disable gradient tracking for efficiency

5
ch06/01_main-chapter-code/ch06.ipynb
View File

@ -777,7 +777,10 @@
" encoded_length = len(encoded_text)\n", " encoded_length = len(encoded_text)\n",
" if encoded_length > max_length:\n", " if encoded_length > max_length:\n",
" max_length = encoded_length\n", " max_length = encoded_length\n",
" return max_length" " return max_length\n",
" # Note: A more pythonic version to implement this method\n",
" # is the following, which is also used in the next chapter:\n",
" # return max(len(encoded_text) for encoded_text in self.encoded_texts)"
] ]
}, },
{ {

3
ch06/01_main-chapter-code/gpt_class_finetune.py
View File

@ -132,6 +132,9 @@ class SpamDataset(Dataset):
if encoded_length > max_length: if encoded_length > max_length:
max_length = encoded_length max_length = encoded_length
return max_length return max_length
# Note: A more pythonic version to implement this method
# is the following, which is also used in the next chapter:
# return max(len(encoded_text) for encoded_text in self.encoded_texts)
def calc_accuracy_loader(data_loader, model, device, num_batches=None): def calc_accuracy_loader(data_loader, model, device, num_batches=None):

3
ch06/02_bonus_additional-experiments/additional_experiments.py
View File

@ -94,6 +94,9 @@ class SpamDataset(Dataset):
if encoded_length > max_length: if encoded_length > max_length:
max_length = encoded_length max_length = encoded_length
return max_length return max_length
# Note: A more pythonic version to implement this method
# is the following, which is also used in the next chapter:
# return max(len(encoded_text) for encoded_text in self.encoded_texts)
def download_and_unzip(url, zip_path, extract_to, new_file_path): def download_and_unzip(url, zip_path, extract_to, new_file_path):

3
ch06/03_bonus_imdb-classification/train_bert_hf_spam.py
View File

@ -51,6 +51,9 @@ class SpamDataset(Dataset):
if encoded_length > max_length: if encoded_length > max_length:
max_length = encoded_length max_length = encoded_length
return max_length return max_length
# Note: A more pythonic version to implement this method
# is the following, which is also used in the next chapter:
# return max(len(encoded_text) for encoded_text in self.encoded_texts)
def download_and_unzip(url, zip_path, extract_to, new_file_path): def download_and_unzip(url, zip_path, extract_to, new_file_path):