Naiw80

joined 10 months ago
sorted by: new top controversial old
Are 7b models useful? in c/localllama@poweruser.forum
[–] Naiw80@alien.top 1 points 9 months ago

Update on this topic...

I realised I've made some mistakes, the reason to start with I asked about 7b models is because the computer I'm using is resource constrained (and normally I use a frontend for the actual interaction)

But because I only have 8GB RAM in the computer I decided to go with llama.cpp and this is obviously where things went wrong.

First of all I obviously messed up the prompt, not that I notice any significant difference now when I realised but it did not follow the expected format for the model I was using.

​

But the key thing appeared to be I've been using the -i (interactive) argument and thought it would work like a chat session, well it appears to do for a few queries but as stated in the original post then all of sudden the model starts to converse with itself (filling in for my queries etc).
But it turns out I should have used --instruct all along, and after I realised now things started to work a lot better (although not perfect).

Finally I decided to give neural-chat a try and dang it appears to do most things I ask it to with great success.

Thanks all for your feedback and comments.

Are 7b models useful? in c/localllama@poweruser.forum
[–] Naiw80@alien.top 1 points 10 months ago

I still evaluate and hopefully thanks to all tips and suggestions here my opinion may change.

Are 7b models useful? in c/localllama@poweruser.forum
Are 7b models useful? in c/localllama@poweruser.forum
[–] Naiw80@alien.top 1 points 10 months ago

Okay thanks

Are 7b models useful? in c/localllama@poweruser.forum
1
Are 7b models useful? (alien.top)
 

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?

Google Brain cofounder says Big Tech companies are lying about the risks of AI wiping out humanity because they want to dominate the market in c/localllama@poweruser.forum
[–] Naiw80@alien.top 1 points 10 months ago

I'm so baffled this has not been realised by people before, it's so obvious and it's not the first time in history it happens either.

First of all Max Tegmark, it's not even the slightest suspicious that his "non profit" organisation received millions of donations from Elon Musk? I have not figured out what Elons stake in this is yet but I have absolutely no doubt in my mind it's economical, basically everything he ever did and said has been to manipulate the Stockmarket etc, I doubt that changed recently.

Then you have OpenAI, that first and formost is everything but Open and very ProprietaryAI nowadays, and what seriously annoys me is that OpenAI in particular been "teasing" about "AGI in n days" etc on several occasions for what purpose if not to manipulate expectations and investors, yet they are one of the most driving in this matter- are people really that stupid that they can't put together 1 and 1?