Recent content by Edgar_

Were you able to progress on this? your specs don't show any GPU acceleration, things are running on the CPU and that's bad for AI, the CPU also looks limited, that probably explains the gibberish. I'd recommend a quick tutorial on how to run colab notebooks that are already made, like the one...

If I'm not mistaken, you added 16 subform controls to an unbound form, and then you're trying to filter with a search mechanism. You're getting the same record multiple times because you have not given the subforms any means to know which record you wish to display, so they display the first...

There are snippets like =MsgBox("message" & Chr(10)... We're gonna get into a different argument there, the syntax for message boxes is interchangeable, but I get your point. By the way, I've been away from the forum for a while, is this "message awaiting mod approval" guard new around here or...

It's cool. I can't say how it's done without trying to replicate it, and I don't claim I will be able to pull it off, but I did my checks and I can see some of the ingredients. There is VBA code to trigger the message boxes though.

What are the specs of the VPS? Have you tried the Colab notebook? The one I posted is uncensored and really quick.

None is objectively better, but Claude tends to be relatively better at code in most languages, and it has come up with more elegant solutions for me in VBA and other languages too. You need to familiarize with context size, which is the amount of things it can remember. It comes to a point...

Yeah, RAM alone isn't enough. I tried this on older computers and they struggled. The CPU matters a lot if you are not using a compatible GPU. If everything runs on the CPU, it can max out and freeze apparently. 8GB of RAM will not be enough with these models. For smoother local use, you really...

I could upgrade to 32GB, and I probably will at some point. What I have now is enough for most tasks. A few days ago I was testing some WAN2.2 video generation models, and I realized my machine simply could not handle the load very well. That led me to try quantized models, and they have been...

I don't know, but I doubt it's because of the available size on your c drive, how much RAM and VRAM do you have? If it's struggling with a 15gb model, try to download a quantized model instead, a Q4 would be smaller and still produce nice results. RAM is the biggest candidate for that message...

I recommend Forgotten Safeword, it's very expressive compared to the others I tested. The size is around 15gb. If you find smaller models, they may not be as expressive and creative, but they also generate good responses

Here's something you can play with, it's a Google Colab notebook that you can just run and it will output a chat UI that lets you talk about anything. Instructions: Go to Google Colab and sign in with a Google account Extract the attached file, it's the notebook Go to File > Upload notebook Go...

It can get very creative, I made it roleplay that it was an aroused piece of VBA code and started telling me "I can be your interpreted s*ut, daddy". It was quite the experience.

It's a gaming laptop I bought 2 years ago, it came with Windows 11. It's a TUF DASH F15, it has an i7 12th gen processor, nvidia Geforce RTX 3070 card with 8GB VRAM, 16GB RAM. I don't play games, sadly, but I do test AI tools all the time. I can generate video, images, and recently, I've been...

I use this tool to fix a lot of the issues with Win11. GitHub - ChrisTitusTech/winutil: Chris Titus Tech's Windows Utility - Install Programs, Tweaks, Fixes, and Updates It needs to be run after every update, Win11 is BS and resets things with the updates. I'm now trying some Kali and it's...

Running it locally gives me multiple advantages. The main advantages: 1. No terms of service 2. No conditions 3. No feature removals 4. No paywall 5. No ads 6. Usage on demand 7. No limitations in the type of questions 8. No limits other than your own machine 9. No ad profiling 10. No spying...