tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-04-02 05:35:19 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Revert model source to mid

Browse Source
This commit is contained in:
kibitzing 2025-10-15 10:29:49 +00:00
parent b48d210795
commit f5001141ec
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/chat_sft.py
View File

@ -34,7 +34,7 @@ from tasks.smoltalk import SmolTalk
# SFT Hyperparameters
run = "dummy" # wandb run name default ("dummy" is special - we won't log to wandb)
# input model options
source = "base" # base|mid , which checkpoint to load the model from (base model or midtrained model)
source = "mid" # base|mid , which checkpoint to load the model from (base model or midtrained model)
model_tag = None # model tag to load the model from (base model or midtrained model)
step = None # step to load the model from (base model or midtrained model)
# compute/precision