• Joined on 2024-05-31
tacit synced commits to refs/pull/94/merge at tacit/nanochat from mirror 2025-10-26 08:12:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/97/merge at tacit/nanochat from mirror 2025-10-26 08:12:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/59/merge at tacit/nanochat from mirror 2025-10-26 08:12:12 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/89/merge at tacit/nanochat from mirror 2025-10-26 08:12:12 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/169/head at tacit/nanochat from mirror 2025-10-26 08:12:12 +00:00
13b97b6088 Merge branch 'karpathy:master' into claude/nanochat-sae-interpretability-011CUT2TocZpFerXthoW9LMf
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/162/merge at tacit/nanochat from mirror 2025-10-26 08:12:12 +00:00
0d8973a53d Merge branch 'karpathy:master' into add-agc-gradient-clipping
Compare 2 commits »
tacit synced commits to refs/pull/147/merge at tacit/nanochat from mirror 2025-10-26 08:12:12 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/85/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/75/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/40/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
05a051dbe9 fix tokenization bug, there should be no space before first letter. sigh
8892470f29 add the SpellingBee task so that nanochat can count r in strawberry etc. along the way we had to add a bunch of new functionality, e.g. extend the calculator to support the count function of python. possibly the current TaskMixture uses way too many synthetic examples of SpellingBee because the eval gives us exactly 100% performance on spelling. We can tune this later to reclaim some wall clock time here I think
81597cd616 move the lr schedule args up in base_train so they are tunable in configurator
Compare 6 commits »
tacit synced commits to refs/pull/30/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/169/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/18/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/63/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
05a051dbe9 fix tokenization bug, there should be no space before first letter. sigh
8892470f29 add the SpellingBee task so that nanochat can count r in strawberry etc. along the way we had to add a bunch of new functionality, e.g. extend the calculator to support the count function of python. possibly the current TaskMixture uses way too many synthetic examples of SpellingBee because the eval gives us exactly 100% performance on spelling. We can tune this later to reclaim some wall clock time here I think
81597cd616 move the lr schedule args up in base_train so they are tunable in configurator
cc3636b01c allow the tokenizer visualize_tokenization to also print the exact token id. you can never be paranoid enough
Compare 5 commits »
tacit synced commits to refs/pull/54/merge at tacit/nanochat from mirror 2025-10-26 00:02:14 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
05a051dbe9 fix tokenization bug, there should be no space before first letter. sigh
8892470f29 add the SpellingBee task so that nanochat can count r in strawberry etc. along the way we had to add a bunch of new functionality, e.g. extend the calculator to support the count function of python. possibly the current TaskMixture uses way too many synthetic examples of SpellingBee because the eval gives us exactly 100% performance on spelling. We can tune this later to reclaim some wall clock time here I think
81597cd616 move the lr schedule args up in base_train so they are tunable in configurator
Compare 6 commits »
tacit synced commits to refs/pull/162/merge at tacit/nanochat from mirror 2025-10-26 00:02:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/162/head at tacit/nanochat from mirror 2025-10-26 00:02:13 +00:00
0d8973a53d Merge branch 'karpathy:master' into add-agc-gradient-clipping
c75fe54aa7 readme tweak, link to new discussion and add file structure
05a051dbe9 fix tokenization bug, there should be no space before first letter. sigh
8892470f29 add the SpellingBee task so that nanochat can count r in strawberry etc. along the way we had to add a bunch of new functionality, e.g. extend the calculator to support the count function of python. possibly the current TaskMixture uses way too many synthetic examples of SpellingBee because the eval gives us exactly 100% performance on spelling. We can tune this later to reclaim some wall clock time here I think
81597cd616 move the lr schedule args up in base_train so they are tunable in configurator
Compare 6 commits »
tacit synced commits to refs/pull/161/merge at tacit/nanochat from mirror 2025-10-26 00:02:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/151/merge at tacit/nanochat from mirror 2025-10-26 00:02:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »
tacit synced commits to refs/pull/141/merge at tacit/nanochat from mirror 2025-10-26 00:02:13 +00:00
c75fe54aa7 readme tweak, link to new discussion and add file structure
Compare 2 commits »