tacit

tacit synced commits to master at tacit/nanochat from mirror 2026-01-05 03:02:37 +00:00

9d4c9b786d many small fixes to base_train: reporting ETA, allowing some additional kwarg flexibility, making sure we don't crash when e.g. depth = 11 - we now calculate the closest num_heads that works

962b6bfba3 alright add transformers as a dep of the repo because it should be easy to evaluate the CORE score of HF models. Not super happy about it but i tried it and the uv.lock doesn't get bloated as much as i expected

ed2082fbc4 sane secrets management

eb7bbc1b66 delete the configurator in favor of argparse and clean up a lot of kwarg details to make them more consistent across all scripts

507d54224a fix small bug where this would break if git stage has deleted files

Compare 6 commits »

tacit synced commits to refs/pull/59/merge at tacit/nanochat from mirror 2026-01-04 18:52:40 +00:00

72801494b7 Merge 23393eae83 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/370/merge at tacit/nanochat from mirror 2026-01-04 18:52:37 +00:00

178b0db5cb Merge 9a9b12b1be into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/328/merge at tacit/nanochat from mirror 2026-01-04 18:52:37 +00:00

75a438db2b Merge 02b22a5a13 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 7 commits »

tacit synced commits to refs/pull/399/merge at tacit/nanochat from mirror 2026-01-04 18:52:37 +00:00

b87ac94db9 Merge de50af6283 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/393/merge at tacit/nanochat from mirror 2026-01-04 18:52:37 +00:00

d652bdaa3f Merge 8b8e94c632 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/141/merge at tacit/nanochat from mirror 2026-01-04 18:52:36 +00:00

ce8d66aeb5 Merge c79559674b into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 8 commits »

tacit synced and deleted reference refs/tags/refs/pull/392/merge at tacit/nanochat from mirror 2026-01-04 18:52:36 +00:00

tacit synced commits to refs/pull/258/merge at tacit/nanochat from mirror 2026-01-04 18:52:36 +00:00

e1182f6ee3 Merge eecfdbf9f9 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 7 commits »

tacit synced commits to refs/pull/32/merge at tacit/nanochat from mirror 2026-01-04 18:52:36 +00:00

92fe420181 Merge f5d35391db into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/405/merge at tacit/nanochat from mirror 2026-01-04 10:42:52 +00:00

79f1cfccd4 Merge 3c4be194e9 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/409/merge at tacit/nanochat from mirror 2026-01-04 10:42:52 +00:00

316e3a9cb4 Merge 4db1d320b45996e765757721254a741753170804 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/407/merge at tacit/nanochat from mirror 2026-01-04 10:42:52 +00:00

a5be1f81d9 Merge 1e04f9846e44fd602ac2232db056fe95c891adb8 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

Compare 4 commits »

tacit synced commits to refs/pull/392/merge at tacit/nanochat from mirror 2026-01-04 10:42:51 +00:00

b6c9e5b41f Merge ccc0016ccd into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/400/merge at tacit/nanochat from mirror 2026-01-04 10:42:51 +00:00

20ee7a251c Merge 32ce342c88 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/396/merge at tacit/nanochat from mirror 2026-01-04 10:42:51 +00:00

793958f1bc Merge 7f6219e092 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 5 commits »

tacit synced commits to refs/pull/324/merge at tacit/nanochat from mirror 2026-01-04 10:42:50 +00:00

e0b3373fde Merge 861cbce2e9 into be56d29b87

be56d29b87 simplify redundant if/elif in bloat metrics

ee79f29fbd replace files-to-prompt with git ls-files for bloat metrics

da8b7ea4cb also delete the rustbpe test code, this now lives in rustbpe repo that is separate

Compare 4 commits »

tacit synced commits to refs/pull/407/merge at tacit/nanochat from mirror 2026-01-04 02:32:41 +00:00

3aab75ad3e Merge 1e04f9846e44fd602ac2232db056fe95c891adb8 into aa42f40e66

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 2 commits »

tacit synced commits to refs/pull/312/merge at tacit/nanochat from mirror 2026-01-04 02:32:40 +00:00

661187ef81 Merge 26b0941f75 into 48abd7d85f

48abd7d85f simplify, clarify and slightly tune model initialization. should be very slightly better possibly, but certainly a lot clearer

10231dfb40 Fix conversation scroll to bottom on some browsers + remove duplicated padding (#348)

389d019a0b small change to doc string at top of tok_train.py (#402)

8c89661465 Update README to match current d34 demo (#314) (#381)

Compare 5 commits »

tacit synced commits to refs/pull/324/merge at tacit/nanochat from mirror 2026-01-04 02:32:40 +00:00

9786a7806e Merge 861cbce2e9 into aa42f40e66

aa42f40e66 delete the inline rustbpe project. it was ugly to have a project within project and rustbpe is now nicely a separate repo on my github karpathy/rustbpe and it's on pypi etc., so we just add it as a depedency to uv. i think it is appropriate that this is a separate repo because 1) it doesn't have too many knobs, other than the ones that are exposed - the regex pattern and vocab size and 2) all of its complexity is not algorithmic (it's equivalent to minbpe), instead it is efficiency-related, so it is ok to hide relatively speaking

Compare 2 commits »