Pinned Loading
-
kron-llm
kron-llm PublicKron is a compact English/Russian language model built from Kronecker-product weights. The 2.85M baseline ships as a 3.3 MB int8 artifact; a 10M model on a 2B-token bilingual corpus is in progress.…
Jupyter Notebook
-
kron-corpus
kron-corpus Public2B-token bilingual English-Russian pretraining corpus with a science accent: math 25%, science 14% (physics, astronomy, cosmology), ML 12%, logic 10%, code 15%, literature 11%. Full provenance per …
Python
-
token-trie
token-trie PublicTokenTrie: Real-time unsupervised sequence prediction engine built on Dynamic Suffix Tries. Implements Context Mixing and Entropy Scaling to capture variable-order dependencies without neural netwo…
Cython
-
lit-graph-agent
lit-graph-agent PublicAutonomous research agent that turns unorganized papers into structured, interactive Obsidian Knowledge Graphs with scientometric ranking, elbow cutoff, and publication-ready bibliographies.
Python
If the problem persists, check the GitHub status page or contact support.