Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

If you go to GroqChat (which is like a demo app), they offer Gemma, Mistral, and LLaMa. These are all open-weights models.


sort by: page size:

> are all open models still just derivatives of llama?

No there are several others but by far the best alongside llama are Mistral’s mistral and mixtral models. Those are called the foundation models which everyone else builds on top of


Mistral opened their weights only for very small LLaMA-like model.

Gemma has a 7B parameters model https://huggingface.co/google/gemma-7b that's what I saw compared to Mistral

(Edit: I'm wrong)


Llama or mistral both are good. Running using ollama

Exactly, nice work BTW. And no hate for Mistral, they're doing great work, but let's not confuse weights-available with fully open models.

The RAW Weights here: https://docs.mistral.ai/models/

This is my favorite model as of now - https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca

It's not top on the Open LLM leaderboards but it's worked well for me. Haven't had a chance to look at Mixtral but this is the one I'd try first - https://huggingface.co/Open-Orca/Mixtral-SlimOrca-8x7B.


The release page has comparisons to Mistral everywhere: https://ai.google.dev/gemma

it uses Mistral or Llama 2

For those that want it, The model mention in the parent is available on Ollama and was updated 3 minutes ago: https://ollama.ai/library/mistra-openorca

You guys are on top of things.



Mistral is not “open source” either since we cannot reproduce it (the training data is not published). Both are open weight models, and they are both released under a license whose legal basis is unclear: it's not actually clear if they own any intellectual property over the model at all. Of course they claim such IP, but no court has ruled on this yet AFAIK and legislators could also enact laws that make these public domain altogether.

In my subjective tests it's not even close to Mistral. While my local gemma is quantized, so is mistral.

But I also tried gemma on huggingface.co/chat which I assume isn't quantized.


I think you're referring to Llama2.

Try Mistral 7B.


Mistral just released the most powerful open weight model in the history of humanity.

How did they weaken their commitment to open weights?



mistral appears to be quite open, and even better than llama imho

This is neat to know. On Ollama, I see mistral and mixtral. Is the latter one the MoE model?

No, they’ve released the weights for Mistral-small. They haven’t released the weights for Mistral-medium.
next

Legal | privacy