Pinned Loading
-
kron-llm
kron-llm PublicKronLLM: a 10M-parameter bilingual English/Russian language model whose weights are Kronecker sums of rank-1 factors instead of dense matrices. Q10 (9,938,886 params) is the model; the 2-3M TinySto…
Python
-
kron-corpus
kron-corpus Public2.78B-token bilingual English/Russian pretraining corpus for KronLLM Q10, the 10M-parameter model: quality-ranked per-language quotas (EN math 26%, encyclopedic 16%, literature 15%, code 11%, CS 10…
Python
-
google-ai-studio-chat-compressor
google-ai-studio-chat-compressor PublicCompress long chats in the Google AI Studio JSON format into compact PDF or Markdown archives. Any chat can be converted with template.json; optional local LLM summaries via Ollama. CLI and PyQt6 GUI.
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
If the problem persists, check the GitHub status page or contact support.