this post was submitted on 16 Nov 2023
1 points (100.0% liked)

LocalLLaMA

4 readers
4 users here now

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

founded 2 years ago
MODERATORS
communick@poweruser.forum
1
Why is Mistral-7b so capable? Any ideas re: dataset? (alien.top)
submitted 2 years ago by Fun_Tangerine_1086@alien.top to c/localllama@poweruser.forum
24 comments fedilink hide all child comments
 

So Mistral-7b is a pretty impressive 7B param model ... but why is it so capable? Do we have any insights into its dataset? Was it trained very far beyond the scaling limit? Any attempts at open reproductions or merges to scale up # of params?

you are viewing a single comment's thread
view the rest of the comments
[–] Charuru@alien.top 1 points 2 years ago

The results are okay, but I'm hard-pressed to call it "very capable". My perspective on it is that other bigger models are making mistakes they shouldn't be making because they were "trained wrong".