fam/nanochat-omni
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: correct minor typos in help text, README, and comments

Browse Source
This commit is contained in:
2bitbit
2026-03-12 17:03:26 +08:00
parent f068604948
commit 2bb93b2ae4
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/tok_train.py
+1 -1
View File
@@ -14,7 +14,7 @@ from nanochat.dataset import parquets_iter_batched
# Parse command line arguments
parser = argparse.ArgumentParser(description='Train a BPE tokenizer')
parser.add_argument('--max-chars', type=int, default=2_000_000_000, help='Maximum characters to train on (default: 10B)')
parser.add_argument('--max-chars', type=int, default=2_000_000_000, help='Maximum characters to train on (default: 2B)')
parser.add_argument('--doc-cap', type=int, default=10_000, help='Maximum characters per document (default: 10,000)')
parser.add_argument('--vocab-size', type=int, default=32768, help='Vocabulary size (default: 32768 = 2^15)')
args = parser.parse_args()