Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
In part five, I started on injecting info about the place the picture was taken into my classifier.
-
I am kind of still amazed how much information exists in mere 7 billion tokens in an ai model (my current preferred model, qwen2.5vl:7b).
-
Most modern systems have some form of face recognizion.
-
Submitting jobs from the command line with RAW API calls works, but isn’t exactly user friendly in the long run.
-
In my previous blog post, I created a basic API that would take a file as input, analyze it in ollama with a vision capable model and return the output.
-
After having tried deepseek a bit, I quickly decided it was more fun to dig a bit deeper.
-
After having played with coding assistants for a while, I decided to let that theme rest for a while.
-
One of the big use-cases for AI for developers today is coding-assistants.
-
After having upgraded my home server, I found myself with an abundance of both CPU power and memory, both of which are meant to be used.
-
In short: I got tired of only having 32 GB memory and not being able to upgrade more.