Pramod Dhungana e19b8b8fe1 Merge branch 'karpathy:master' into fix/source-argparse-choices		2026-03-01 09:04:16 -05:00
..
base_eval.py	small touchups to the eval script, re-order items etc, cosmetic	2026-02-03 21:03:42 +00:00
base_train.py	fix minor bug in fp8 application to skip tiny matmuls	2026-02-18 23:17:29 +00:00
chat_cli.py	fix(chat_cli,chat_eval): add --source choices and validate --task-name to avoid KeyError	2026-03-01 09:02:57 -05:00
chat_eval.py	fix(chat_cli,chat_eval): add --source choices and validate --task-name to avoid KeyError	2026-03-01 09:02:57 -05:00
chat_rl.py	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
chat_sft.py	tune the data mixture a bit, load optimizer by default when SFT. These were confirmed to be best settings from sweeps of sft	2026-02-18 15:49:18 +00:00
chat_web.py	fix(chat_web): use removeprefix for SSE chunk to avoid corrupting payload when token contains 'data: '	2026-03-01 08:49:15 -05:00
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