6 Commits

Author	SHA1	Message	Date
rehman	09bdfd6628	fix: truncate conversation tokens to model context window in chat_cli ... Fixes #581. When conversation_tokens grows beyond model.config.sequence_len, engine.generate() received a zero-dimension tensor and crashed with a matmul shape error. Add a sliding window guard before each generate() call that keeps the most recent (sequence_len - max_new_tokens) tokens, re-inserts bos to preserve a well-formed sequence, and notifies the user when truncation occurs.	2026-05-06 01:29:20 +05:00
Andrej Karpathy	1076f97059	delete autocast, an unnecessary thorn in my side, manage dtypes directly	2026-03-04 23:55:30 +00:00
Sofie Van Landeghem	72b9064f9d	remove leftover mid references (#491)	2026-02-02 08:33:46 -08:00
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
karpathy	2e9669e03a	upgrading all other files to be able to use cpu/mps as well as cuda. various minor other changes ,e.g. changing max_iterations to num_iterations in sft script for consistency in naming	2025-10-20 10:15:17 -07:00
karpathy	3a5e0bc50b	initial commit	2025-10-13 06:49:24 -07:00