Do all of these models, regardless of parameters, support tool use and structured output?
Yes they all support tool use at least.
Mistral 3 family of models released
181–190 of 243 posts
Re: Mistral 3 family of models released
#182The new large model uses DeepseekV2 architecture. 0 mention on the page lol. It's a good thing that open source models use the best arch available. K2 does the same but at least mentions "Kimi K2 was designed to further scale up Moonlight, which employs an architecture similar to DeepSeek-V3". --- vllm/model_executor/models/mistral_large_3.py ``` from vllm.model_executor.models.deepseek_v2 import DeepseekV3ForCausalL…
So they spent all of their R&D to copy deepseek, leaving none for the singular novel added feature: vision. To quote the hf page: >Behind vision-first models in multimodal tasks: Mistral Large 3 can lag behind models optimized for vision tasks and use cases.
Well, behind "models" not "langual models".
Of course models purely made for image stuff will completely wipe it out. The vision language models are useful for their generalist capabilities
Re: Mistral 3 family of models released
#183Re: Mistral 3 family of models released
#184Earlier quoted context omitted.
I'm reading this post and wondering what kind of crazy accessibility tools one could make. I think it's a little off the rails but imagine a tool that describes a web video for a blind user as it happens, not just the speech, but the actual action.
This is not local but Gemini models can process very long videos and provide description with timestamps if asked for. https://ai.google.dev/gemini-api/docs/video-understanding#tr...
Nor would it be describing things as they happen, but instead needing pre-processing, so in the end, very different :)
Re: Mistral 3 family of models released
#185Earlier quoted context omitted.
Mistral are mostly focusing on b2b, and for customers that want to self-host (banks and stuff). So their founders being from Meta, or where their cloud platform are hosted, are entirely irrelevant to the story.
The fact they would not exist without the leeches and built their business on the leeches is irrelevant. Pan-nationalism is a hell of a drug: a company that does not know you exist puts out an objectively awful release, and people take frank discussion of it as a personal slight.
If you want to allocate capital efficiently planet-scale you have to ignore nations to the largest extent possible.
Re: Mistral 3 family of models released
#186The new large model uses DeepseekV2 architecture. 0 mention on the page lol. It's a good thing that open source models use the best arch available. K2 does the same but at least mentions "Kimi K2 was designed to further scale up Moonlight, which employs an architecture similar to DeepSeek-V3". --- vllm/model_executor/models/mistral_large_3.py ``` from vllm.model_executor.models.deepseek_v2 import DeepseekV3ForCausalL…
I don't think it's fair to demand everything be open and then get mad when they open-ness is used. It's an obsessive and harmful double standard.
Re: Mistral 3 family of models released
#187Earlier quoted context omitted.
Guessing GP commenter considers Apache more "open" than Meta's license. Which to be fair isn't terrible but also not quite as clean as straight apache
Llama's license explicitly disallows its usage in the EU. If that doesn't even meet the threshold for "terrible", then what does?
Why does it disallow usage in the EU?
Re: Mistral 3 family of models released
#188Anyone succeed in running it with vLLM?
The instruct models are available on Ollama (e.g. `ollama run ministral-3:8b`), however the reasoning models still are a wip. I was trying to get them to work last night and it works for single turn, but is still very flakey w/ multi-turn.
Re: Mistral 3 family of models released
#189I see several 3.x versions on Openrouter.ai, any idea which of those are the new models?