[HN Gopher] Mistral AI launches Mixtral-Next
       ___________________________________________________________________
        
       Mistral AI launches Mixtral-Next
        
       Author : varunvummadi
       Score  : 182 points
       Date   : 2024-02-17 03:46 UTC (19 hours ago)
        
 (HTM) web link (chat.lmsys.org)
 (TXT) w3m dump (chat.lmsys.org)
        
       | AnujNayyar wrote:
       | No indication that this a MoE (Mistral not Mixtral).
       | 
       | Very exciting nevertheless, here's hoping the bless the OS
       | community once again!
        
       | ismailmaj wrote:
       | Could it be Mistral Large? This beats GPT-4 on my personal test.
        
         | ta988 wrote:
         | 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.
        
         | furyofantares wrote:
         | I tried a bunch of my recent prompts to GPT-4 from daily use -
         | this was often just slightly worse, sometimes slightly better.
         | Fast too (tokens per second) while also not being overly wordy
         | - very much appreciated that.
         | 
         | Refusals are a bit "I am just a language model"-y which GPT-4
         | has gotten away from. Also it's more refuse-y if I broach
         | something rudely (which again I've found GPT-4 to have become
         | much better at.)
         | 
         | Way better at everything than whichever Gemini I've been trying
         | recently (can't tell for sure what I'm using when I use it.)
         | But that one isn't even in contention for any use at all IME.
         | 
         | Overall it felt like I need to try it in daily use to work out
         | if it's a contender with GPT-4 as a daily driver.
        
           | CuriouslyC wrote:
           | The clincher for me will be if the API to it is not so
           | exorbitantly priced as GPT4, and if mistral can make using
           | LoRAs economical.
        
       | tmikaeld wrote:
       | This 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"
        
       | mattpavelle wrote:
       | For those unfamiliar with the LMSys interface:
       | 
       | Click/tap on "Direct Chat" in the top tab navigation and you can
       | select "mistral-next" as model.
        
         | pama wrote:
         | 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?
        
         | cubefox wrote:
         | I only get the message "Connection errored out."
        
       | aunetx wrote:
       | It's quite funny to use! It is better when speaking French than
       | chat gpt3.5 on my opinion
        
         | mratsim wrote:
         | It is a French company so maybe they have extra French
         | datasets?
         | 
         | I've been quite disappointed by French LLMs on Huggingface when
         | I tried a month ago.
        
           | kergonath wrote:
           | Mistral models tend to be quite good at non-English
           | languages. French of course, but also Spanish, German and
           | Italian. From what I have read it's something they consider
           | important when training their models.
        
       | twobitshifter wrote:
       | AIExplained 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.
        
         | MasterScrat wrote:
         | And how does Mistral do "accurate long content retrieval"?
        
           | twobitshifter wrote:
           | see the long range performance piece here
           | https://arxiv.org/pdf/2401.04088.pdf
        
       | justanotherjoe wrote:
       | wow, this might be the best LLM that i've used in terms of
       | phrasing and presenting the answers.
        
       | bloopernova wrote:
       | Slightly related question: what's a good coding LLM to run on a
       | 4070 12GB card?
       | 
       | Also, do coding LLMs use treesitter to "understand" code?
        
         | sob727 wrote:
         | I'm also interested in the answer to that.
        
           | explorigin wrote:
           | Depends on what you want to use it for. I use deepseek-coder
           | v1 (1.5 is too verbose). I use it like a customized web
           | search to quickly build one-off scripts in python.
           | 
           | If you're wanting something to be your hands so you don't
           | have to type, open-source LLMs and IDE integration is not
           | reliably there yet. Follow the AIDER discord to stay up on
           | the latest in this area.
        
         | ianschmitz wrote:
         | I'm pretty new to running these locally, but here's my
         | understanding:
         | 
         | Best models currently: codellama or deepseek coder. 6.7B or 1B
         | depending on how much latency you can tolerate
         | 
         | Treesittee: from looking at the logs of the chat completions
         | requests for Continue or Twinny extensions for VS Code, they
         | both appear to just send a chunk of the document as well as a
         | special placeholder to indicate where the cursor currently is.
        
         | wiradikusuma wrote:
         | Another one is
         | https://github.com/WisdomShell/codeshell/blob/main/README_EN...
         | and it has its own IntelliJ plugin.
        
         | Havoc wrote:
         | Try deepseek 6.7B
        
         | fancy_pantser wrote:
         | > do coding LLMs use treesitter...?
         | 
         | It's up to the app to put that into the context. Generally,
         | coding LLMs do well if you provide them the source tree, graph,
         | search results, notable files, etc in the context. The is how
         | Sourcegraph's Cody product works, for example.
        
       | mrfakename wrote:
       | Note that it's actually "Mistral Next" not "Mixtral Next" - so it
       | isn't necessarily a MoE. For example, an early version of Mistral
       | Medium (Miqu) was not a MoE but instead a Llama 70B model. I
       | wonder how many parameters this one has
        
         | zettabomb wrote:
         | I know what they were going for with the Mixtral name but every
         | time I come across it I wonder if they considered just how
         | easily the two might be confused. It seems like a poor branding
         | decision - what if some expected the Mixtral performance but
         | accidentally uses a Mistral model? What if someone wants the
         | low resource usage of e.g. Mistral 7B but tries out Mixtral
         | 8x7B instead? It's especially hard when your colleagues aren't
         | necessarily native English speakers.
         | 
         | There's got to be a better name for such a cool product. Maybe
         | MistralX? MistMix?
        
           | exe34 wrote:
           | I feel like this is not really an issue. I personally lost
           | track of all the llamas, <not>gpts, etc - but if somebody is
           | going to seriously use a certain model, they'll find out soon
           | enough if they're using the wrong one.
        
             | zettabomb wrote:
             | It has definitely affected myself and colleagues, perhaps
             | we didn't waste much time but it's annoying. Even if it
             | isn't a problem, it really cannot hurt to make the naming
             | easier to understand.
        
           | mrfakename wrote:
           | I agree. I also think the Llama naming was confusing -
           | versioning by capitalization? (LLaMA vs Llama)
        
       | lolinder wrote:
       | Mistral's process for releasing new models is _extremely_ low-
       | information. After getting very confused by this link I tried
       | looking for a link that has _any_ better information, and there
       | just isn 't one.
       | 
       | I thought Mixtral's release was weird when they just pasted a
       | magnet link [0] into Twitter with no information, but at least
       | people could download and analyze it so we got some reasonable
       | third-party commentary in between that and the official
       | announcement. With this one there's nothing at all to go on
       | besides the name and the black box.
       | 
       | [0] https://news.ycombinator.com/item?id=38570537
        
         | kaycebasques wrote:
         | Company creates blackbox technology, and the company's
         | communications are themselves like a blackbox... fitting
         | 
         | (I know that Mistral does a lot more stuff in the open than
         | other companies, just couldn't resist the parallel between this
         | and the blackbox limitations of LLMs in general)
        
       | redder23 wrote:
       | You can literally type "woke shit" in and you get woke shit out.
       | I am so impressed.
        
       | vitorgrs wrote:
       | From my tests, it did better than Gemini Ultra on a few
       | reason/logic questions.
        
       | apapapa wrote:
       | The Together.AI logo at the bottom is very hard to read... (Dark
       | gray on black)
        
       | xeckr wrote:
       | As someone who has only been using GPT-4 since its release, I am
       | pleasantly surprised by how far open LLMs have come.
        
       ___________________________________________________________________
       (page generated 2024-02-17 23:01 UTC)