Andrej Karpathy 1ddaad1c1c nuke midtraining from orbit, it's not as needed now that we have a BOS-aligned dataloader. Also change the README a lot. midtrianing is not yet fully properly erased across the board, but good enough for step 1

2026-01-31 19:12:25 +00:00

..

base_eval.py

bugfix

2025-12-26 19:02:12 +08:00

base_loss.py

update the CPU/MPS script to give reasonable results. The model can at least answer that Paris is the capital of France and knows that the sky is blue, for about 40 minutes of training on my macbook. Also fixed a bug that existed due to KVCache bfloat16 dtype assumption

2026-01-17 12:27:30 -08:00

base_train.py

warmdown of 0.5 is slightly better:

2026-01-31 01:08:44 +00:00

chat_cli.py

nuke midtraining from orbit, it's not as needed now that we have a BOS-aligned dataloader. Also change the README a lot. midtrianing is not yet fully properly erased across the board, but good enough for step 1

2026-01-31 19:12:25 +00:00

chat_eval.py

nuke midtraining from orbit, it's not as needed now that we have a BOS-aligned dataloader. Also change the README a lot. midtrianing is not yet fully properly erased across the board, but good enough for step 1

2026-01-31 19:12:25 +00:00

chat_rl.py

Combine AdamW and Muon into single MuonAdamW optimizer, cleaner, ty @chrisjmccormick for idea/help

2026-01-29 00:52:08 +00:00

chat_sft.py

nuke midtraining from orbit, it's not as needed now that we have a BOS-aligned dataloader. Also change the README a lot. midtrianing is not yet fully properly erased across the board, but good enough for step 1

2026-01-31 19:12:25 +00:00

chat_web.py

feat: allow top_k=0 in web api to disable filtering (#458)

2026-01-30 09:21:41 -08:00

tok_eval.py

initial commit

2025-10-13 06:49:24 -07:00

tok_train.py

quick fix to not OOM main speedrun script

2026-01-26 22:31:42 +00:00