wassname/ml-debug
1
0
Fork 0
mirror of https://github.com/wassname/ml-debug.git synced 2026-06-27 15:16:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: drop links to deleted/tombstone gists (repo is canonical now)

Browse Source 
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-06-11 16:55:04 +08:00
parent 0837f27f08
commit 30ac76053e
3 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
PLAYBOOK.md
+1 -1
View File
@@ -223,4 +223,4 @@ Folklore sources (the quotes above trace to these):
For modern transformer pretraining specifically (the sources above predate it), see [Karpathy's recipe](https://karpathy.github.io/2019/04/25/recipe/) and the [nanochat deepwiki](https://deepwiki.com/karpathy/nanochat) (320+ empirical HP sweeps for a GPT-2-scale run). Most multi-source claims trace to quotes in [docs/ml_debug_folklore.argdown](docs/ml_debug_folklore.argdown) (vargdown); the full evidence set is in [docs/evidence/](docs/evidence/). For modern transformer pretraining specifically (the sources above predate it), see [Karpathy's recipe](https://karpathy.github.io/2019/04/25/recipe/) and the [nanochat deepwiki](https://deepwiki.com/karpathy/nanochat) (320+ empirical HP sweeps for a GPT-2-scale run). Most multi-source claims trace to quotes in [docs/ml_debug_folklore.argdown](docs/ml_debug_folklore.argdown) (vargdown); the full evidence set is in [docs/evidence/](docs/evidence/).
Curated by [wassname](https://github.com/wassname). Companion gist: https://gist.github.com/wassname/d72da69ffe1bdb60cdb1708bd3b5c535 Curated by [wassname](https://github.com/wassname).
SKILL.md
+1 -1
View File
@@ -324,4 +324,4 @@ Folklore sources (the quotes above trace to these):
For modern transformer pretraining specifically (most sources above predate it), see [Karpathy's recipe](https://karpathy.github.io/2019/04/25/recipe/) and the [nanochat deepwiki](https://deepwiki.com/karpathy/nanochat) (320+ empirical HP sweeps for a GPT-2-scale run). For LLM-as-judge eval debugging workflow more broadly, Hamel Husain's ["Your AI Product Needs Evals"](https://hamel.dev/blog/posts/evals/) covers the error-analysis-first approach for LLM products. Most multi-source claims trace to quotes in [docs/ml_debug_folklore.argdown](docs/ml_debug_folklore.argdown) (vargdown); the full evidence set is in [docs/evidence/](docs/evidence/). For modern transformer pretraining specifically (most sources above predate it), see [Karpathy's recipe](https://karpathy.github.io/2019/04/25/recipe/) and the [nanochat deepwiki](https://deepwiki.com/karpathy/nanochat) (320+ empirical HP sweeps for a GPT-2-scale run). For LLM-as-judge eval debugging workflow more broadly, Hamel Husain's ["Your AI Product Needs Evals"](https://hamel.dev/blog/posts/evals/) covers the error-analysis-first approach for LLM products. Most multi-source claims trace to quotes in [docs/ml_debug_folklore.argdown](docs/ml_debug_folklore.argdown) (vargdown); the full evidence set is in [docs/evidence/](docs/evidence/).
Curated by [wassname](https://github.com/wassname). Companion gist: https://gist.github.com/wassname/d72da69ffe1bdb60cdb1708bd3b5c535 Curated by [wassname](https://github.com/wassname).
pinn/SKILL.md
-3
View File
@@ -6,9 +6,6 @@ description: "PINN (Physics-Informed Neural Network) training best practices and
# PINN Training Best Practices # PINN Training Best Practices
https://gist.github.com/wassname/a68314f731002b32aa637c3d43a081c9/edit
Consolidated from: NeuralPDE.jl tests/docs, ConFIG repo, Wang et al. 2021, Rathore et al. 2024 (ICML), ml_debug folklore, and practical experience. Heat-exchanger-specific notes in [refs/heat_exchanger.md](refs/heat_exchanger.md). Consolidated from: NeuralPDE.jl tests/docs, ConFIG repo, Wang et al. 2021, Rathore et al. 2024 (ICML), ml_debug folklore, and practical experience. Heat-exchanger-specific notes in [refs/heat_exchanger.md](refs/heat_exchanger.md).
Epistemic status: Patterns confirmed across multiple sources. Where sources disagree, noted. Paper claims marked with credence estimates. Epistemic status: Patterns confirmed across multiple sources. Where sources disagree, noted. Paper claims marked with credence estimates.