This one is based on llama 2, first one worked very well for rule and structure following with guidance so I’m highly intrigued to see if this lives up to the previous
I am getting very poor results with this model. Its coding ability is noticeably worse than LLaMa 2. It will readily produce output that claims to be following a logical progression of steps, but often the actual answer is not consistent with the logic or the steps themselves are in fact not correct or logical.
Curious to know if other people who have tried it are getting the same results.
I’ve been beating my head against a docker issue for a couple days so didn’t get to try this one yet, but I did notice vicuna was VERY ready to output code and pretty coherently i might add, should check that one out if you’re interested in coding ability
I haven’t tried that one yet because it seemed like an older model with a less refined dataset but I will put that one in the queue as the next model to download and try out.