jmorganca
A core maintainer of the Ollama open-source project, responsible for code review and release management of the project.
Timeline (last 90 days)
The change #18967 submitted by contributor jmorganca added the q2_0 tensor type and corresponding file type support to the GGUF format.
Ollama v0.40.4 upgrades llama.cpp to version b11521, committed by jmorganca, mainly aimed at support for decision models and EmbeddingGemma 2.
The commit was signed by project maintainer jmorganca and released with a verified signature through GitHub.
All Facts (3)
The commit was signed by project maintainer jmorganca and released with a verified signature through GitHub.
50%UnverifiedThe change #18967 submitted by contributor jmorganca added the q2_0 tensor type and corresponding file type support to the GGUF format.
50%UnverifiedOllama v0.40.4 upgrades llama.cpp to version b11521, committed by jmorganca, mainly aimed at support for decision models and EmbeddingGemma 2.
50%