Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mistral AI launches Mixtral-Next

chat.lmsys.org

Post reply on HN
Print view View original

11–20 of 55 posts

Re: Mistral AI launches Mixtral-Next

#12

Post by furyofantares »

ismailmaj wrote: post #3

Could it be Mistral Large? This beats GPT-4 on my personal test.

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.

Re: Mistral AI launches Mixtral-Next

#14

Post by CuriouslyC »

furyofantares wrote: post #12
ismailmaj wrote: post #3

Could it be Mistral Large? This beats GPT-4 on my personal test.

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.) Wa…

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.

Re: Mistral AI launches Mixtral-Next

#16

Post by ianschmitz »

bloopernova wrote: post #13

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?

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.

Re: Mistral AI launches Mixtral-Next

#17

Post by explorigin »

sob727 wrote: post #15
bloopernova wrote: post #13

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?

I'm also interested in the answer to that.

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.

Re: Mistral AI launches Mixtral-Next

#18

Post by mrfakename »

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

Re: Mistral AI launches Mixtral-Next

#20

Post by wiradikusuma »

bloopernova wrote: post #13

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?

Another one is https://github.com/WisdomShell/codeshell/blob/main/README_EN... and it has its own IntelliJ plugin.
Post reply on HN