Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added --input-file-encoding as a command line argument #10

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added --input-file-encoding as a command line argument #10

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions makemore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -542,10 +542,10 @@ def __getitem__(self, idx):
y[len(ix)+1:] = -1 # index -1 will mask the loss at the inactive locations
return x, y

def create_datasets(input_file):
def create_datasets(input_file, input_file_encoding : str = None):

# preprocessing of the input text file
with open(input_file, 'r') as f:
with open(input_file, 'r', encoding=input_file_encoding) as f:
data = f.read()
words = data.splitlines()
words = [w.strip() for w in words] # get rid of any leading or trailing white space
Expand Down Expand Up @@ -604,6 +604,7 @@ def next(self):
parser.add_argument('--max-steps', type=int, default=-1, help="max number of optimization steps to run for, or -1 for infinite.")
parser.add_argument('--device', type=str, default='cpu', help="device to use for compute, examples: cpu|cuda|cuda:2|mps")
parser.add_argument('--seed', type=int, default=3407, help="seed")
parser.add_argument('--input-file-encoding', type=str, default=None, help='encoding of the input file')
# sampling
parser.add_argument('--top-k', type=int, default=-1, help="top-k for sampling, -1 means no top-k")
# model
Expand All @@ -626,7 +627,7 @@ def next(self):
writer = SummaryWriter(log_dir=args.work_dir)

# init datasets
train_dataset, test_dataset = create_datasets(args.input_file)
train_dataset, test_dataset = create_datasets(args.input_file, args.input_file_encoding)
vocab_size = train_dataset.get_vocab_size()
block_size = train_dataset.get_output_length()
print(f"dataset determined that: {vocab_size=}, {block_size=}")
Expand Down