11d • 💬 General discussion
I fine tuned a model and it works 100x better than any massive model ever could!
So this has been a bit of a learning experience for me. I’ve tried to find tuning models in the past, but to know what was available and not get anywhere, things didn’t quite click.
However, this time, I took a different approach—using the latest Liquid AI model, LFM 2.5.1b.1.2. This was a game-changer for me because I wanted to train a reasoning model that could think quickly, produce fast outputs, and excel at coding tasks. And it worked!
We’ve successfully implemented it, and it’s now available for you to try out on your devices. We’re excited to see how you’ll use it and can’t wait to hear your thoughts.
This model is designed to run efficiently across a variety of devices—think smartphones, Raspberry Pi, computers, or even a laptop.
The possibilities are truly endless! I’m really looking forward to seeing what we can achieve with this technology.
And here’s a quick question: Would you ever want to build your own model and explore its potential for specific use cases?
0
0 comments
I fine tuned a model and it works 100x better than any massive model ever could!
skool.com/open-source-ai-builders-club
The #1 Club for all developers, builders and innovators in Open Source AI, Automation & Robotics!
Leaderboard (30-day)
1
+2
2
+1
3
+1
4
+1
Powered by