Earlier quoted context omitted.
Unless you're a lawyer. We love 'em.
As a journalist, same!
Also a journalist. I use em-dashes all the time
Magistral — the first reasoning model by Mistral AI
61–70 of 444 posts
Re: Magistral — the first reasoning model by Mistral AI
#62Benchmarks suggest this model loses to Deepseek-R1 in every one-shot comparison. Considering they were likely not even pitting it against the newer R1 version (no mention of that in the article) and at more than double the cost, this looks like the best AI company in the EU is struggling to keep up with the state-of-the-art.
This reads like an AI-generated comment. What do you mean by "benchmarks suggest"? The benchmarks are very clear and presented right there in the page.
Re: Magistral — the first reasoning model by Mistral AI
#63Re: Magistral — the first reasoning model by Mistral AI
#64I 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…
Their paper https://mistral.ai/static/research/magistral.pdf is also cool! They edited GRPO via: 1. Removed KL Divergence 2. Normalize by total length (Dr. GRPO style) 3. Minibatch normalization for advantages 4. Relaxing trust region
> Removed KL Divergence
Wait, how are they computing the loss?
Re: Magistral — the first reasoning model by Mistral AI
#65How many other open-weights reasoning models are there? Is it possible to run multiple reasoning models on one problem? (Why not? I guess). Another funny thought is: they release their Small model, and kept their Medium as a premium service. I wonder if you could do chains with Medium run occasionally, linked together by local runs of Small?
Qwen 3 and DeepSeek R1 and Phi-4 Reasoning are the best open weights reasoning models I know of.
Re: Magistral — the first reasoning model by Mistral AI
#66How many other open-weights reasoning models are there? Is it possible to run multiple reasoning models on one problem? (Why not? I guess). Another funny thought is: they release their Small model, and kept their Medium as a premium service. I wonder if you could do chains with Medium run occasionally, linked together by local runs of Small?
Just Deepseek I think and there are distillations of that that can run on consumer hardware if you really want.
Re: Magistral — the first reasoning model by Mistral AI
#67Benchmarks suggest this model loses to Deepseek-R1 in every one-shot comparison. Considering they were likely not even pitting it against the newer R1 version (no mention of that in the article) and at more than double the cost, this looks like the best AI company in the EU is struggling to keep up with the state-of-the-art.
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.
Re: Magistral — the first reasoning model by Mistral AI
#68The 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
Re: Magistral — the first reasoning model by Mistral AI
#69A few days after Apple's "The illusion of Reasoning". I wonder if this is the same again. Anyone runs Tower of Hanoi?
The illussion of reasoning was terrible paper. 2^n-1 how it could fit in context size. I tried o3 and he gave me python script saying that inserting all moves is to much for context window. completely different results.
I think that their point was that the problem is easily solvable by humans without code, and shows the ability to chain steps together to achieve a goal.
Re: Magistral — the first reasoning model by Mistral AI
#70Earlier quoted context omitted.
Their paper https://mistral.ai/static/research/magistral.pdf is also cool! They edited GRPO via: 1. Removed KL Divergence 2. Normalize by total length (Dr. GRPO style) 3. Minibatch normalization for advantages 4. Relaxing trust region
> Removed KL Divergence Wait, how are they computing the loss?
Oh it's the KL term sorry - beta * KL ie they set beta to 0.
The goal of it was to "force" the model not to stray to far away from the original checkpoint, but it can hinder the model from learning new things