This commit is contained in:
Sofie Van Landeghem 2026-03-10 19:23:19 -07:00 committed by GitHub
commit 0e38c49050
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -21,6 +21,9 @@ if [ -z "$WANDB_RUN" ]; then
WANDB_RUN=dummy
fi
# wipe the report
python -m nanochat.report reset
# train tokenizer on ~2B characters (~34 seconds on my MacBook Pro M3 Max)
python -m nanochat.dataset -n 8
python -m scripts.tok_train --max-chars=2000000000
@ -63,3 +66,6 @@ python -m scripts.chat_sft \
# Chat with the model over a pretty WebUI ChatGPT style
# python -m scripts.chat_web
# generate final report
python -m nanochat.report generate