this post was submitted on 24 Nov 2023
1 points (100.0% liked)

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
1
Are 7b models useful? (alien.top)
submitted 11 months ago by Naiw80@alien.top to c/localllama@poweruser.forum
24 comments fedilink hide all child comments
 

I'm struggling to get the 7b models to do something useful, obviously I'm doing something wrong as it appears many people strive for 7b models.

But myself I can not get them to follow instructions, they keep repeating stuff and occasionally they start to converse with themselves.

Does anyone have any pointers what I'm doing wrong?

you are viewing a single comment's thread
view the rest of the comments
[–] vatsadev@alien.top 1 points 11 months ago (4 children)

OpenHermes 2.5 is amazing from what I've seen. it can call functions, summarize text, is extremely competitive, all the works

[–] shivam2979@alien.top 1 points 11 months ago

Haven’t you noticed slower inference from OpenHermes 2.5 compared to other 7B models?

[–] _ralph_@alien.top 1 points 11 months ago (2 children)

How does it function call? Some internal api?

[–] Shoddy_Vegetable_115@alien.top 1 points 11 months ago

It returns a JSON with function name and respective arguments which you can parse later in the program and call the function with those arguments given by the model.

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

I'm seconding that. I'm actually amazed by how it performs, frequently getting similar or better answers than bigger models. I start to think that we do lose a lot with quantization from the bigger models...

[–] Relevant_Outcome_726@alien.top 1 points 11 months ago

Can you provide the prompt for function call?