11–20 of 203 posts
These benchmark numbers cannot be real for a 7b model
I loaded up a random 12B model on ollama the other day and couldn't believe how good it competent it seemed and how fast it was given the machine I was on. A year or so ago, that would have not been the case.
These benchmark numbers cannot be real for a 7b model
The smaller models have been creeping upward. They don't make headlines because they aren't leapfrogging the mainline models from the big companies, but they are all very capable. I loaded up a random 12B model on ollama the other day and couldn't believe how good it competent it seemed and how fast it was given the machine I was on. A year or so ago, that would have not been the case.
They could've called it Xiaomimo.
These benchmark numbers cannot be real for a 7b model
...and searching for things related to multiple antennae just got harder. They could've called it Xiaomimo.
Earlier quoted context omitted.
The smaller models have been creeping upward. They don't make headlines because they aren't leapfrogging the mainline models from the big companies, but they are all very capable. I loaded up a random 12B model on ollama the other day and couldn't believe how good it competent it seemed and how fast it was given the machine I was on. A year or so ago, that would have not been the case.
exactly, it seems to validate my assumption from some time ago, that we will mostly use local models for everyday tasks.
We just need Google or Apple to provide their own equivalent of both: Ollama and OpenRouter so user either use inference for free with local models or BringYourOwnKey and pay themself for tokens/electricity bill. We then just charge smaller fee for renting or buying our cars.
These benchmark numbers cannot be real for a 7b model
The smaller models have been creeping upward. They don't make headlines because they aren't leapfrogging the mainline models from the big companies, but they are all very capable. I loaded up a random 12B model on ollama the other day and couldn't believe how good it competent it seemed and how fast it was given the machine I was on. A year or so ago, that would have not been the case.
Problem was that of a top ten book recommendations only the first 3 existed and the rest was a casually blended hallucination delivered in perfect English without skipping a beat.
"You like magic? Try reading the Harlew Porthouse series by JRR Marrow, following the orphan magicians adventures in Hogwesteros"
And the further towards the context limit it goes the deeper this descent into creative derivative madness it goes.
It's entertaining but limited in usefulness.
Earlier quoted context omitted.
The smaller models have been creeping upward. They don't make headlines because they aren't leapfrogging the mainline models from the big companies, but they are all very capable. I loaded up a random 12B model on ollama the other day and couldn't believe how good it competent it seemed and how fast it was given the machine I was on. A year or so ago, that would have not been the case.
exactly, it seems to validate my assumption from some time ago, that we will mostly use local models for everyday tasks.