repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
Tencent/AngelSlim
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
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) · 46%Condensing Large-Scale Datasets Directly with Minimal Information Loss →
- PossiblePossibly related (embedding) · 45%Helix-7B →
- PossiblePossibly related (embedding) · 45%bigcode/starcoder →
- PossiblePossibly related (embedding) · 53%Tencent releases Hy3 open-source model that allegedly matches models up to five times its active size - the-decoder.com →
- PossiblePossibly related (embedding) · 49%BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression →
- PossiblePossibly related (embedding) · 48%Tencent-HY3 is the real deal on 128GB! →
- PossiblePossibly related (embedding) · 50%Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data →
- PossiblePossibly related (embedding) · 53%Lossless model compression experiment: GLM-5.2 in 25% less memory →
Implements
Related to
Covers (incoming)
Implements (incoming)
Related across the graph
paperBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compressionmodelbigcode/starcodernewsTencent releases Hy3 open-source model that allegedly matches models up to five times its active size - the-decoder.comnewsLossless model compression experiment: GLM-5.2 in 25% less memorypaperCondensing Large-Scale Datasets Directly with Minimal Information LossnewsTencent-HY3 is the real deal on 128GB!paperRequential Coding: Pushing the Limits of Model Compression with Self-Generated Training DatamodelHelix-7B