If you want factual answers from a local model it might help to turn the temperature down.
It would also help if I had more VRAM and wasn't running a 7B parameter 4-bit quantized model.
> If you want factual answers from a local model it might help to turn the temperature down.
This makes sense. If you interact with a language model and it says something wrong it is your fault
You're not "interacting with a language model", you're running a program (llama.cpp) with a sampling algorithm which is not set to maximum factualness by default.
It's like how you have to set x264 to the anime tuning or the film tuning depending on what you run it on.
Actually isn't this good? It means we can run something multiple times to prove itself a bad answer?
You can ask LLMs the same question and they might sometimes get it wrong and other times get it right. Having different answers is no indication that none of them is correct.
Furthermore, even if an LLM always gives the same answer to a question, there’s no guarantee the answer is correct.
An LLM will always give the same output for the same input. It’s sorta like a random number generator that gives the same list of “random” numbers for the same seed. LLMs get a seed too.
That’s irrelevant for the matter. The person I replied to obviously did not have seeded responses in mind.
It can tell you if the answer is wrong, but it can never tell you if the answer is right.
You should specify the model size and temperature.
For fact retrieval you need to use temperature 0.
If you don't get the right facts then try 34b, 70b, Mixtral, Falcon 180b, or another highly ranked one that has come out recently like DBRX.
> Brooklyn Nets won the 1986 Cricket World Cup by scoring 46 yards in only 3 frames
LLM's hallucinations are insidous because they have the ring of truth around them. yards and frames aren't cricket terms, so we're off to the races with them.