Hacker News new | past | comments | ask | show | jobs | submit
Gecko4072 | on: LFM2.5 2.6B model competitive with 4x larger models
These LiquidAI models have never worked well for me in practice.
eurekin | parent | next
Care to share any details? I'm about to check the 2.6b lfm on document editing.
BoredomIsFun | parent
I agree. They have serious issues with coherence.