LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Just spreading awareness towards this very useful Model. (alien.top)

submitted 11 months ago by Haiart@alien.top to c/localllama@poweruser.forum

9 comments fedilink hide all child comments

Hi. I am not behind the model in any capacity nor those who are asked me to do so, before anyone asks.
I am just a normal LLM enjoyer that wants better 13B models in the near future, because at the moment, they're being plummeted onto the ground by many Mistral 7B finetunes and since we don't have any Mistral 13B base model...

The Model in question is this one right here, which seems to be flying under the radar for some reason:
https://huggingface.co/sequelbox/DaringFortitude
TheBloke already did his magic on it, just search his profile on Hugging Face with Ctrl+F.

The reason as to why I am doing this is: I honestly think this is a really, really good (I did some little testing, but my machine is garbage to test any further) and useful Base Model for further finetuning/merging and etc...

top 9 comments

sorted by: hot top controversial new old

[–] frozen_tuna@alien.top 1 points 11 months ago

This model is primarily recommended as a superior-to-Llama-2 baseline for additional finetuning,

According to the model, its not really supposed to compete with something like Vicuna. Sounds like they're trying to be an upgraded foundational model.

[–] ttkciar@alien.top 1 points 11 months ago

What have you found it useful for? The model card is pretty vague.

[–] eachcitizen100@alien.top 1 points 11 months ago

its model average on the openllm leaderboard is 51.

[–] kpodkanowicz@alien.top 1 points 11 months ago

Really nice, I had a dreamz we need to find a way to iterate over base models so every finetune is closer to sota :D

[–] Creative_Bottle_3225@alien.top 1 points 11 months ago (1 children)

53 GB?

[–] a_beautiful_rhind@alien.top 1 points 11 months ago

it's in FP32 rather than FP16

[–] Budget-Juggernaut-68@alien.top 1 points 11 months ago

I really wonder who this TheBlok is. What a legend.

[–] sophosympatheia@alien.top 1 points 11 months ago

I can't speak to the quality of sequelbox/DaringFortitude but I can wholeheartedly recommend sequelbox/StellarBright. I have been using StellarBright in some experimental 70b model merges and it's phenomenal. I imagine 13b merges using DaringFortitude, or finetunes on top of it, would be quite good.

[–] FPham@alien.top 1 points 11 months ago

There is very little info.

It seems to be instruction finetuned, but what template? ChatML? There is no mention of anything. Posting it this way is pretty bad.