-
1080 Ti Returns
Upgraded my server with an old 1080 Ti GPU, enhancing its capacity by nearly doubling the available VRAM. This change cut processing time for a batch job from 47 days to about 37 days, improving overall efficiency. Read More
-
Speeding Up Ollama
Discuss optimizing performance while managing tasks with limited GPU resources. I implemented a continuous job queue and a web interface to prioritize tasks with the Hermes Agent. Future enhancements include automating document processing and utilizing different models for varied tasks. Read More
-
A partial self-portrait from an unfinished archive
An AI-assisted pass through a vast WordPress archive reveals a persistent pattern: learning through hands-on creation, probing systems for hidden failure modes, championing civic transparency, and translating complex technical curiosity into tangible tools, public history, and active community participation. Read More
-
Unlocking the Potential of Hermes for AI Tasks
An old Raspberry Pi workshop series aimed to boost digital literacy at the library through eight interactive sessions covering foundational computing, coding, and electronics skills for ages 13 and up. Funding challenges necessitated exploring alternative solutions for materials and support. Read More
-
Hermes & Honcho
Setting up Hermes, an orchestrator within the Ollama framework. Highlighting features such as improved context management, a visually appealing interface, and the ability to run various models locally. Despite some installation challenges, Hermes enabled effective task execution and process spawning. Read More