Mistral AI launches Mixtral-Next
chat.lmsys.org
Mistral AI launches Mixtral-Next
1–10 of 55 posts
Re: Mistral AI launches Mixtral-Next
#2No indication that this a MoE (Mistral not Mixtral).
Very exciting nevertheless, here’s hoping the bless the OS community once again!
Re: Mistral AI launches Mixtral-Next
#3Could it be Mistral Large?
This beats GPT-4 on my personal test.
Re: Mistral AI launches Mixtral-Next
#4This was linked randomly on Mistrals Discord chat, nothing "official" yet.
It's a preview of their newest prototype model.
To use it, click "Direct Chat" tab and choose "Mistral next"
Re: Mistral AI launches Mixtral-Next
#5For those unfamiliar with the LMSys interface:
Click/tap on "Direct Chat" in the top tab navigation and you can select "mistral-next" as model.
Re: Mistral AI launches Mixtral-Next
#6For those unfamiliar with the LMSys interface: Click/tap on "Direct Chat" in the top tab navigation and you can select "mistral-next" as model.
From limited experimentation, and within the confines of a single prompt (rather than a full chat), this model seems reasonably interesting. Does anyone have good examples of QA that showcase the capabilities compared to other advanced models?
Re: Mistral AI launches Mixtral-Next
#7It's quite funny to use! It is better when speaking French than chat gpt3.5 on my opinion
Re: Mistral AI launches Mixtral-Next
#8AIExplained on youtube has guessed that Gemini 1.5 pro is taking Mistral’s accurate long content retrieval and Google just scaled it as much as they could. The Gemini 1.5 pro paper has a citation back to the last mistral paper in 2024.
Re: Mistral AI launches Mixtral-Next
#9wow, this might be the best LLM that i've used in terms of phrasing and presenting the answers.
Re: Mistral AI launches Mixtral-Next
#10Could it be Mistral Large? This beats GPT-4 on my personal test.
It doesn't on mine it still is really wrong but compared to mixtral when you tell next that it did a mistake it corrects it to the right answer where mixtral was making things up that were even more wrong.