tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-05-25 09:08:05 +00:00
Code Issues Actions 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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
runs/speedrun.sh
View File

@ -58,8 +58,8 @@ python -m nanochat.dataset -n 8
# See comment below for why 370 is the right number here
python -m nanochat.dataset -n 370 &
DATASET_DOWNLOAD_PID=$!
# train the tokenizer with vocab size 2**16 = 65536 on ~2B characters of data
python -m scripts.tok_train --max-chars=2000000000 --vocab-size=65536
# train the tokenizer with vocab size 2**15 = 32768 on ~2B characters of data
python -m scripts.tok_train
# evaluate the tokenizer (report compression ratio etc.)
python -m scripts.tok_eval

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()