Stanford Lectures...
A few days ago Stanford dumped a whole pile of AI/ML lectures up on their youtube. They're a pretty good watch if you get bored and want to dive more into this stuff.
A few days ago Stanford dumped a whole pile of AI/ML lectures up on their youtube. They're a pretty good watch if you get bored and want to dive more into this stuff.
YouTubeIt's been a few weeks since I've posted or made any changes on Wilmer; I haven't stopped or lost interest, but rather I'm about to change jobs and I've been heads down on transition stuff before I leave my current
I was trying to answer someone's question about how Llama.cpp handles offloading with Mixture of Experts models on a regular gaming PC with a 24GB GPU, and ended up spending a few hours in a deep dive.
When I first started Wilmer, it was for a very specific reason: I wanted a semantic router, and one didn't yet exist. The routers that were available were all specifically designed to take the last message, categorize that, and route you that way. I needed more, though; what
So this looks like it could actually be a really fun model https://huggingface.co/microsoft/UserLM-8b I like this little specific purpose LLMs the most because it opens up some neat doors. They likely made this to act as the user-proxy in autogen, and they point out on their