tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-04-04 06:35:23 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge c655043092 into 2f09686724

Browse Source
This commit is contained in:
aioaneid 2026-02-13 14:22:46 +01:00 committed by GitHub
commit f60cd0eb36
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
runs/runcpu.sh
View File

@ -22,7 +22,7 @@ if [ -z "$WANDB_RUN" ]; then
fi
# train tokenizer on ~2B characters (~34 seconds on my MacBook Pro M3 Max)
python -m nanochat.dataset -n 8
python -m nanochat.dataset -n 11
python -m scripts.tok_train --max-chars=2000000000
python -m scripts.tok_eval

6
runs/speedrun.sh
View File

@ -49,9 +49,9 @@ python -m nanochat.report reset
# Tokenizer
# Download the first ~2B characters of pretraining dataset
# each data shard is ~250M chars
# so we download 2e9 / 250e6 = 8 data shards at this point
# each shard is ~100MB of text (compressed), so this is about ~800MB of data on disk
# each data shard is ~250M chars, but due to the `doc_cap` only ~200M chars are used.
# so we download 2e9 / 200e6 + 1 = 11 data shards at this point
# each shard is ~90MB of text (compressed), so this is about ~1GB of data on disk
# look at dev/repackage_data_reference.py for details on how this data was prepared
python -m nanochat.dataset -n 8
# Immediately also kick off downloading more shards in the background while tokenizer trains