deftdawg's starred repositories
matmulfreellm
Implementation for MatMul-free LM.
cohere-toolkit
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
micro-agent
An AI agent that writes (actually useful) code for you
distributed-llama
Tensor parallelism is all you need. Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.
ExploitGSM
Exploit for 6.4 - 6.5 kernels and another exploit for 5.15 - 6.5
RepoToTextForLLMs
Automate the analysis of GitHub repositories for LLMs with RepoToTextForLLMs. Fetch READMEs, structure, and non-binary files efficiently. Outputs include analysis prompts to aid in comprehensive repo evaluation
captive-browser
A dedicated Chrome instance to log into captive portals without messing with DNS settings.
BinaryVectorDB
Efficient vector database for hundred millions of embeddings.
ha-mysmartblinds
MySmartBlinds component for Home Assistant
init-flake
Reproducible kernel and initramfs