• Joined on 2024-05-31
tacit synced commits to refs/pull/663/merge at tacit/nanochat from mirror 2026-03-25 22:25:15 +00:00
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 3 commits »
tacit synced commits to refs/pull/644/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
7b70f6b411 Merge pull request #639 from mathieu-lacage/master
47e983eea7 fix: use meta device in disable_fp8 to avoid VRAM spike (#616)
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 6 commits »
tacit synced and deleted reference refs/tags/refs/pull/639/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
tacit synced commits to refs/pull/641/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 3 commits »
tacit synced commits to refs/pull/610/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 2 commits »
tacit synced commits to refs/pull/646/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 3 commits »
tacit synced commits to master at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
7808dc7159 Merge pull request #595 from svlandeg/fix/typo
a4ed96687b Merge pull request #634 from 2bitbit/fix-docs-and-comments
7b70f6b411 Merge pull request #639 from mathieu-lacage/master
47e983eea7 fix: use meta device in disable_fp8 to avoid VRAM spike (#616)
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
Compare 16 commits »
tacit synced commits to refs/pull/655/merge at tacit/nanochat from mirror 2026-03-25 22:25:14 +00:00
c0dbf1f3ff use COMPUTE_DTYPE-aware cast in Muon polar express step
Compare 2 commits »
tacit synced and deleted reference refs/tags/refs/pull/595/merge at tacit/nanochat from mirror 2026-03-25 22:25:13 +00:00
tacit synced and deleted reference refs/tags/refs/pull/616/merge at tacit/nanochat from mirror 2026-03-25 22:25:13 +00:00
tacit synced and deleted reference refs/tags/refs/pull/634/merge at tacit/nanochat from mirror 2026-03-25 22:25:13 +00:00
tacit synced commits to refs/pull/614/merge at tacit/nanochat from mirror 2026-03-25 14:15:22 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to refs/pull/659/merge at tacit/nanochat from mirror 2026-03-25 14:15:22 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to refs/pull/588/merge at tacit/nanochat from mirror 2026-03-25 14:15:22 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
Compare 2 commits »
tacit synced commits to refs/pull/655/merge at tacit/nanochat from mirror 2026-03-25 06:13:42 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to master at tacit/nanochat from mirror 2026-03-25 06:13:41 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
tacit synced commits to refs/pull/551/merge at tacit/nanochat from mirror 2026-03-25 06:13:41 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to refs/pull/540/merge at tacit/nanochat from mirror 2026-03-25 06:13:41 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to refs/pull/611/merge at tacit/nanochat from mirror 2026-03-25 06:13:41 +00:00
4e1694cc95 bunch of ideas tried from openai/parameter-golf, all negative results for nanochat
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 4 commits »
tacit synced commits to refs/pull/663/merge at tacit/nanochat from mirror 2026-03-24 22:03:43 +00:00
1cd94d768f bump D:N ratio to 12 per recent scaling laws re-run
c16db281ff fix small bug with params logging and batch size
Compare 3 commits »