osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

Improve readability of huge numbers

Browse Source 
Before:
  length of dataset in characters:  1115394
  all the unique characters: 
   !$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
  vocab size: 65
  train has 1003854 tokens
  val has 111540 tokens

After:
  length of dataset in characters: 1,115,394
  all the unique characters: 
   !$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
  vocab size: 65
  train has 1,003,854 tokens
  val has 111,540 tokens
This commit is contained in:
リョウゼ 2023-01-16 22:05:32 +01:00 committed by GitHub
parent 7f74652843
commit be571fff2c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
data/shakespeare_char/prepare.py
View File

@ -17,13 +17,13 @@ if not os.path.exists('input.txt'):
with open('input.txt', 'r') as f: with open('input.txt', 'r') as f:
data = f.read() data = f.read()
print("length of dataset in characters: ", len(data)) print(f"length of dataset in characters: {len(data):,}")
# get all the unique characters that occur in this text # get all the unique characters that occur in this text
chars = sorted(list(set(data))) chars = sorted(list(set(data)))
vocab_size = len(chars) vocab_size = len(chars)
print("all the unique characters:", ''.join(chars)) print("all the unique characters:", ''.join(chars))
print("vocab size:", vocab_size) print(f"vocab size: {vocab_size:,}")
# create a mapping from characters to integers # create a mapping from characters to integers
stoi = { ch:i for i,ch in enumerate(chars) } stoi = { ch:i for i,ch in enumerate(chars) }
@ -41,8 +41,8 @@ val_data = data[int(n*0.9):]
# encode both to integers # encode both to integers
train_ids = encode(train_data) train_ids = encode(train_data)
val_ids = encode(val_data) val_ids = encode(val_data)
print(f"train has {len(train_ids)} tokens") print(f"train has {len(train_ids):,} tokens")
print(f"val has {len(val_ids)} tokens") print(f"val has {len(val_ids):,} tokens")
# export to bin files # export to bin files
train_ids = np.array(train_ids, dtype=np.uint16) train_ids = np.array(train_ids, dtype=np.uint16)