Not obsessed with the local stuff because I'm more interested in battery life and ease of use, but I set up Continue with an Anthropic and Mixtral API key and this baby is great. I was coming from Copilot but this setup has a much better UX and it's way smarter. Definitely sticking with this
I really like the idea of using a local AI model. I’m wondering if this set up allows you to find tune a model and run it locally? I would also be interested in perhaps using a RAG scenario to help with more specific or use case driven scenarios.
![I.N "HALLUCINATION" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/n5B5q1Hwt_U/mqdefault.jpg)
I've been using it to deepen my understanding of every kind of code. Taking advantage of my own GPU. It's absolutely killer
Ah! I knew my Ryzen 9 would come in handy soon enough!
I have one already. With that, I feel myself lucky.
I pray with whole of my Heart for you to get one quite soon!🙏🙂
I need one but no money
For this stuff you’d be better off investing in a good GPU with 16GB+ VRAM.
Not obsessed with the local stuff because I'm more interested in battery life and ease of use, but I set up Continue with an Anthropic and Mixtral API key and this baby is great.
I was coming from Copilot but this setup has a much better UX and it's way smarter. Definitely sticking with this
Can you guide me please? How do I do this, please?
@@96144 I actually switched to using Zed but it was Mixtral's autocomplete and Anthropic's top model, now I'm using Claude and Copilot in Zed
I really like the idea of using a local AI model. I’m wondering if this set up allows you to find tune a model and run it locally? I would also be interested in perhaps using a RAG scenario to help with more specific or use case driven scenarios.
why we should try a locally hosted AI model while there are cloud solutions available for the IDEs?
Cost
Nicely explained inside 👍
Try "Qwen 2" model. It is very good.
Thank you for this tutorial. This will be helpful for my commercial projects.
what is your browser?
Are there benchmarks for any of this?
Has anyone tried using openai apis and calculated if the cost were less then copilot?
Since it's pay as you go, it would really depend on how much you use code with it.
LM studio does not work on my windows PC. the error message after trying to load is "not conpatable with the system. any Ideas ?
Thx for sharing this! This is very handy! Now I might quit using co-pilot or ChatGPT!
This is good. But this puts a heavy load on system
Not if you run a small model
Very true. Just used cloud solutions , like the Codeium plugin for VS Code
use this instead of vscode, this is faster & better, i'm using only this in my daily job.
I'll stick to IDX
By Google? 😂 I am sure they will kill it in three years time.
Try OpenDevin
It makes many errors.