Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
etemiz 
posted an update 10 days ago
Post
475
Mistral Small 3.1 numbers are in. It is interesting Mistral always lands in the middle.
https://sheet.zoho.com/sheet/open/mz41j09cc640a29ba47729fed784a263c1d08?sheetid=0&range=A1

I started to do the comparison with 2 models now. In the past Llama 3.1 70B Q4 was the one doing the comparison of answers. Now I am using Gemma 3 27B Q8 as well to have a second opinion on it. Gemma 3 produces very similar measurement to Llama 3.1. So the end result is not going to shake much.
JLouisBiz

You are mixing free software models with proprietary models. This makes no sense because proprietary doesn't give the freedom to user to do what the user wants.

What is Free Software? - GNU Project - Free Software Foundation
https://www.gnu.org/philosophy/free-sw.html

There are people, who, out of respect, and knowledge of what is "freedom", do not even touch proprietary models. Any development on Llama models, for example, impedes the progress in society.

Any development with free software models like Qwen (majority are with the free/libre license) and Deepseek, and Microsoft Phi models, IBM Granite, Allen AI Olmo, etc. -- such developments foster the progress and help parties build on top of them without legal worries.

Meta’s LLaMa 2 license is not Open Source – Open Source Initiative
https://opensource.org/blog/metas-llama-2-license-is-not-open-source

In this post