Show HN: Horus-runtime – Train your own tiny LLM from scratch
W-29 · Tiny LLM From Scratch - TinyStories Pretrain & Sample Overview A fast, small-data companion to W-28: pretrains the same from-scratch decoder-only Transformer, but on TinyStories (short, simple GPT-generated children's stories, a couple hundred MB) instead of the Pile (~900GB). It exists for people who want to see a from-scratch LLM learn something legible in minutes on a laptop, without the Pile's disk/bandwidth requirements. It skips instruction tuning and eval entirely.
- ▪W-29 · Tiny LLM From Scratch - TinyStories Pretrain & Sample Overview A fast, small-data companion to W-28: pretrains the same from-scratch decoder-only Transformer, but on TinyStories (short, simple GPT-generated children's stories, a coup
- ▪It exists for people who want to see a from-scratch LLM learn something legible in minutes on a laptop, without the Pile's disk/bandwidth requirements.
- ▪It skips instruction tuning and eval entirely.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,214 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/temple-compute/pantheon/tree/main/workflows/ai/w02-tiny-llm |
| Publication time | Sat, 01 Aug 2026 09:27:21 +0000 |
| Retrieval time | 2026-08-01T09:35:41.571Z |
| Last seen | 2026-08-01T09:35:41.571Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | dLdfi49cgg75 · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
W-29 · Tiny LLM From Scratch - TinyStories Pretrain & Sample Overview A fast, small-data companion to W-28: pretrains the same from-scratch decoder-only Transformer, but on TinyStories (short, simple GPT-generated children's stories, a couple hundred MB) instead of the Pile (~900GB). It exists for people who want to see a from-scratch LLM learn something legible in minutes on a laptop, without the Pile's disk/bandwidth requirements. It skips instruction tuning and eval entirely. The deliverable is a pretrained checkpoint plus a sample generation proving it learned to continue a story prompt.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.