Reading the repo — stats and the shipped feed land in about ten seconds…
Videos, notes and experiments to understand deep learning
1.2k 767 9 openLast shipped 10d ago
Videos, notes and experiments to understand deep learning
A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in Deep-Learning-Experiments's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
gpt2_val_tinystories: re-run notebook with fine-tuned model, fix eval loop (no collator, transpose batch); README: add fine-tune results (49,683 steps, ppl 5.33→3.44)
gpt2_tinystories: rewrite fine-tune script (docs, eval+perplexity, resume, separate output dir); fix validation notebooks; commit from-scratch checkpoint; correct README numbers
Add README summarizing GPT2/TinyStories train & validation results; link from main README
gpt2_val_tinystories_fr_scratch: use latest English TinyStories checkpoint (gpt2-tinystories-final), token-weighted perplexity, drop duplicate eval cell
gpt2_tinystories_fr_scratch: add full documentation, enable eval + perplexity metric, fix imports
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
