tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-03-25 22:25:13 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

remove model tag

Browse Source
This commit is contained in:
svlandeg 2026-02-27 00:20:19 +01:00
parent 0fe9acb8c0
commit 212bdae120
2 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
runs/runcpu.sh
View File

@ -47,7 +47,6 @@ python -m scripts.base_eval --device-batch-size=1 --split-tokens=16384 --max-per
# SFT (~10 minutes on my MacBook Pro M3 Max)
curl -L -o $NANOCHAT_BASE_DIR/identity_conversations.jsonl https://karpathy-public.s3.us-west-2.amazonaws.com/identity_conversations.jsonl
python -m scripts.chat_sft \
--model-tag=d6 \
--eval-every=200 \
--eval-tokens=524288 \
--num-iterations=1500 \

2
runs/speedrun.sh
View File

@ -82,7 +82,7 @@ torchrun --standalone --nproc_per_node=8 -m scripts.base_eval -- --device-batch-
curl -L -o $NANOCHAT_BASE_DIR/identity_conversations.jsonl https://karpathy-public.s3.us-west-2.amazonaws.com/identity_conversations.jsonl
# run SFT and eval the model
torchrun --standalone --nproc_per_node=8 -m scripts.chat_sft -- --model-tag=d26 --run=$WANDB_RUN
torchrun --standalone --nproc_per_node=8 -m scripts.chat_sft -- --run=$WANDB_RUN
torchrun --standalone --nproc_per_node=8 -m scripts.chat_eval -- -i sft
# chat with the model over CLI! Leave out the -p to chat interactively