ros/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-30 04:22:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

quick fix to not OOM main speedrun script

Browse Source
This commit is contained in:
Andrej Karpathy
2026-01-26 22:31:42 +00:00
parent 85b3e95e09
commit 8630d32be4
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/tok_train.py
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=10_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: 10B)')
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()