This is the greatest AI chat model yet
And it's not even close. This is the one to keep.
Yeah, it's pretty dam good at story writing too!
I nearly dismissed it as its 1-shot stories are pretty terrible, but it does a good job if asked to self-critique and refine...
Goliath-120B on the other hand wrote good 1-shot Grimdark stories but would refuse to listen and just wanted to carry on writing more and more.
VERY impressed!
(it does suck at coding though)
I have started getting a "model overloaded" as of today, and I have no clue why it says this. I thought it meant too many people were using it, but it feels that message would come up before today as well, so it's not that...
I tried to ask itself why it gave the message, but it still gave the same message. I was able to say test and it worked, but then it gave the message after I tried another response.
Extremely Intelligent model, adept at logic, answer "which is heavier 1 kg feather or 2 kg feather?" correctly, while Llama 3 failed
I strongly agree, but what puzzles me is that this model’s MMLU score is lower than that of Llama3 70B, which is clearly different from my tests (chat testing). This model’s capabilities far exceed those of Llama3, and I even believe that this model surpasses Claude3 sonet in abilities.
Anyone tested this model as an agent?
(编写代码能力，不如OpenAi Gpt3.5，推理能力也不如Gpt3.5，如果GPT-3.5编写代码能力都不如，我想说这个怎么和GPT-4相比？)
我认为他需要重新训练，比如（回香炉重新训练）