Skip to content

david-thrower/cerebros-core-algorithm-alpha

View on GitHub ↗Related repositories →

The Cerebros package is an ultra-precise Neural Architecture Search (NAS) / AutoML that is intended to much more closely mimic biological neurons than conventional neural network architecture strategies.

active 2023-08-272026-07-20 (UTC)

Complete coverage26,481 / 26,481 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
1.6K
Pushes
1.1K
Pull requests
56
Issues
191
Stars
15
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 1059 days from 2023-08-27 to 2026-07-20. Pushes: 1,082 total, peak 37 in a day. Pull requests: 56 total, peak 6 in a day. Issues: 191 total, peak 14 in a day. Comments: 96 total, peak 9 in a day. Stars: 15 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
david-thrower1.3K1K3380
sashakolpakov7246106
Aidyn-Lopez40995
Thunderblok231530
Copilot9005
Shohail-Ismail2000
Abdulnaser971010

Recent activity

Latest issues, pull requests and releases

  • Issue#315david-thrower2026-01-23 00:21
    from-314-add-gpu-metrics
  • Issue#314david-thrower2026-01-22 23:52
    from-312-debug-jax-version-gpu-compat
  • Issue#312david-thrower2026-01-22 17:48
    from-311-add-automated-dockerhub-push-of-container
  • Issue comment#309david-thrower2026-01-21 17:29
    from-307-dockerize-the-best-run-from-HPO-study
  • Issue#308david-thrower2026-01-16 21:02
    patch-fix-init-of-not-gpt-to-work-in-other-tf-versions
  • Issue comment#308david-thrower2026-01-16 21:02
    patch-fix-init-of-not-gpt-to-work-in-other-tf-versions
  • Issue#308david-thrower2026-01-16 18:24
    patch-fix-init-of-not-gpt-to-work-in-other-tf-versions
  • Issue#307david-thrower2026-01-16 05:30
    tiny-stories-96-seq-len-hpo-run-from-305
  • Issue#306david-thrower2026-01-15 20:52
    from-305-dev-of-composite-llm-jupyter-demo
  • Issue comment#303david-thrower2026-01-13 01:18
    from-302-2026-01-12--hpo-run
  • Issue#301david-thrower2026-01-08 04:37
    from-300-fix-layer-build-issue-and-computational-optimizations
  • Issue#300david-thrower2026-01-05 23:24
    from-297-extend-manifold-hyperconnect-tocerebros-block
  • Issue#299david-thrower2026-01-05 23:21
    add-compute-output-spec-to-attention-layers
  • Issue comment#299david-thrower2026-01-05 23:21
    add-compute-output-spec-to-attention-layers
  • Issue#299david-thrower2026-01-04 22:26
    add-compute-output-spec-to-attention-layers
  • Issue#299david-thrower2026-01-04 22:26
    add-compute-output-spec-to-attention-layers
  • Issue#299david-thrower2026-01-04 22:26
    add-compute-output-spec-to-attention-layers
  • Issue#299david-thrower2026-01-04 22:26
    add-compute-output-spec-to-attention-layers
  • Issue#297david-thrower2026-01-04 22:23
    add-a-manifold-hyperconnectivity-layer
  • Issue comment#297david-thrower2026-01-04 22:23
    add-a-manifold-hyperconnectivity-layer
  • Issue#297david-thrower2026-01-04 21:17
    add-a-manifold-hyperconnectivity-layer
  • Issue#296david-thrower2026-01-04 19:07
    add-optional-debug-logs-for-generate-loop
  • Issue#294david-thrower2026-01-04 18:19
    possible-bug-revise-logic-for-repetition-penalty-in-generate-loop
  • Issue#294david-thrower2026-01-04 18:19
    possible-bug-revise-logic-for-repetition-penalty-in-generate-loop
  • Issue#294david-thrower2026-01-04 18:19
    possible-bug-revise-logic-for-repetition-penalty-in-generate-loop

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 15 stars here means stars gained during the window, not the repo's star count.