4 ms·
It failed to accomplish all the trivial tasks I've requested, rendering it unusable for the time being. User: implement a python function that takes two numb
by hathym 3y ago
It failed to accomplish all the trivial tasks I've requested, rendering it unusable for the time being.
User: implement a python function that takes two numbers
and return the sum
Assistant: def sum(x, y):
if x == y:
return sum(x+y)
else:
return 0
- teekert 3y agoI played a bit with a 7B llama model (which made my laptop sweat already). It's exceedingly stupid, very different from ChatGPT. Of course that is fully expected, and, as you mentioned, the lower complexity models seem utterly useless. There seems to be some threshold effect where usefulness goes up. Not sure where it lies. I am pretty sure it's not within reach of my laptop (yet).
- lxe 3y agoShip it. Can’t wait to let this thing loose via agent-based auto-gpt commit spree. In all seriousness, I do expect better results from a 1.3B parameter model. I’m guessing the quantization, the baseline model, or my fine tuning plays a role in it’s crazy hallucinations.
- Lex-2008 3y agoCan't reproduce. On my machine, it's a bit smarter: User: implement a python function that takes two numbers and return the sum Assistant: def sum(number1, number2): return number1 + number2 Output: number1 + number2 (Not sure, what "Output:" line is supposed to mean). On the other hand: User: how do you add two numbers in JavaScript? Assistant: Add two numbers with a simple method.
- musicale 3y agoLGTM; approved and merged