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

Magistral — the first reasoning model by Mistral AI

mistral.ai

Post reply on HN
Print view View original

121–130 of 444 posts

Re: Magistral — the first reasoning model by Mistral AI

#121

Post by monkmartinez »

danielhanchen wrote: post #3

I made some GGUFs for those interested in running them at https://huggingface.co/unsloth/Magistral-Small-2506-GGUF ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL or ./llama.cpp/llama-cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.7 --top-k -1 --top-p 0.95 -ngl 99 Please use --jinja for llama.cpp and use temperature = 0.7, top-p 0.95! Also best to increase Ollama's context length…

At the risk of dating myself; Unsloth is the Bomb-dot-com!!! I use your models all the time and they just work. Thank you!!! What does llama.cpp normally use if not "jinja" for their templates?

Re: Magistral — the first reasoning model by Mistral AI

#122

Post by paulddraper »

esafak wrote: post #98
tootie wrote: post #67

Earlier quoted context omitted.

As an occasional user of Mistral, I find their model to give generally excellent results and pretty quickly. I think a lot of teams are now overly focused on winning the benchmarks while producing worse real results.

If so we need to fix the benchmarks.

https://en.wikipedia.org/wiki/Goodhart%27s_law

Re: Magistral — the first reasoning model by Mistral AI

#123

Post by meta_ai_x »

8n4vidtmkvmk wrote: post #94
derektank wrote: post #88

Earlier quoted context omitted.

And, perhaps most relevantly, the regulatory environment the people are working in. French people working in America are probably more productive than French people working in France (if for no other reason because they probably work more hours in America than France).

Are we sure more time butt in office equates to more productivity?

Yes, especially in cutting edge research areas where other high functioning people with high energy isarelso there.

You can write your in-house CRUD app in your basement or your office and it doesn't matter.

The vast majority of HN crowd and general social/mainstream media don't make the difference between these two scenarios

Re: Magistral — the first reasoning model by Mistral AI

#124

Post by riku_iki »

esafak wrote: post #98
tootie wrote: post #67

Earlier quoted context omitted.

As an occasional user of Mistral, I find their model to give generally excellent results and pretty quickly. I think a lot of teams are now overly focused on winning the benchmarks while producing worse real results.

If so we need to fix the benchmarks.

those who try to fix them are fighting alone against huge corps which try to abuse them..

Re: Magistral — the first reasoning model by Mistral AI

#125

Post by meta_ai_x »

mrtksn wrote: post #42
atemerev wrote: post #37

Earlier quoted context omitted.

I live in Europe.

Cool, which regulations exactly stopped you from doing cutting edge AI?

regulation-culture breed a certain type of risk-taking culture. So, you can't blame a specific regulation for lack of innovation culture

Re: Magistral — the first reasoning model by Mistral AI

#126

Post by saratogacx »

rafram wrote: post #30

Is the number of em-dashes in this marketing copy indicative of the kind of output that the model produces? If so, might want to tone it down a bit.

That is just Mistral's market style. You see it on a lot of their pages. The model output doesn't share the same love for the long dash.

Re: Magistral — the first reasoning model by Mistral AI

#127

Post by whiplash451 »

derektank wrote: post #88
pdabbadabba wrote: post #84

Earlier quoted context omitted.

For the purposes of GP's comment, I think the nationalities of the people actually running the company and doing the work are more relevant than who has invested.

And, perhaps most relevantly, the regulatory environment the people are working in. French people working in America are probably more productive than French people working in France (if for no other reason because they probably work more hours in America than France).

> they probably work more hours in America than France

Not sure that's even true. Mistral is known to be a really hard-working place

Re: Magistral — the first reasoning model by Mistral AI

#128

Post by NitpickLawyer »

simonw wrote: post #117
diggan wrote: post #68

The only mention of tools I could find is this: > it significantly improves project planning, backend architecture, frontend design, and data engineering through sequenced, multi-step actions involving external tools or API. I'm guessing this means it was trained with tool calling? And if so, does that mean it does tool calling within the thinking/reasoning, or within the main text? Seems unclear

Tool calling isn't enabled in the official Magistral Small GGUF (or the Ollama one) which is sad. Hope they (or someone else) fix that soon.

They have already released Devstral, which is a tool-specific finetune of the same base model. That works pretty well with cline (even though it was specifically tuned for open-hands).

This would likely be a good model for the "plan" mode in various agentic tools (cline, aider, cursor/windsurf/void, etc). So you'd have a chat in plan mode, then use devstral to actually implement that plan.

Re: Magistral — the first reasoning model by Mistral AI

#129

Post by 1propionyl »

8n4vidtmkvmk wrote: post #94
derektank wrote: post #88

Earlier quoted context omitted.

And, perhaps most relevantly, the regulatory environment the people are working in. French people working in America are probably more productive than French people working in France (if for no other reason because they probably work more hours in America than France).

Are we sure more time butt in office equates to more productivity?

Yes, specifically when it comes to open-ended research or development, collocation is non-negotiable. There are greater than linear benefits in creativity of approach, agility in adapting to new intermediate discoveries, etc that you get by putting a number of talented people who get along in the same space who form a community of practice.

Remote work and flattening communication down to what digital media (Slack, Zoom, etc) afford strangle the beneficial network effects.

Re: Magistral — the first reasoning model by Mistral AI

#130

Post by micromacrofoot »

yeahforsureman wrote: post #91
saubeidl wrote: post #51

Earlier quoted context omitted.

The cookie banners are corps trying to circumvent the rights and protections. If they actually went by the spirit of the protections, the cookie banners wouldn't be needed. Your ire is misdirected.

Are you sure? The ePrivacy Directive requires a (GDPR-level) consent for just placing the cookie, unless it's strictly necessary for the provision of the “service”. The way EU regulators interpret this, even web analytics falls outside the necessity exception and therefore requires consent. So as long as the user doesn't and/or is not able to automatically signal consent (or non-consent) eg via general browser-level…

there are analytics providers that don't require third party cookies, it's not hard to switch
Post reply on HN