repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1h ago
MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%How're you deploying LLMs in production now-a-days? What's the best and most affordable way? [D] →
- PossiblePossibly related (embedding) · 48%Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs →
- PossiblePossibly related (embedding) · 46%What's one local AI workflow you wish you'd discovered sooner? →
- PossiblePossibly related (embedding) · 48%Suggestion: Lets setup a wiki for LLM model config, fixes etc →
Covers
Covers (incoming)
Related across the graph
newsSuggestion: Lets setup a wiki for LLM model config, fixes etcnewsHow're you deploying LLMs in production now-a-days? What's the best and most affordable way? [D]newsShow HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIsnewsWhat's one local AI workflow you wish you'd discovered sooner?