ContinueDev + CodeQwen : STOP PAYING for Github's Copilot with this LOCAL & OPENSOURCE Alternative

In this video, I'll be telling you about a new local and free github copilot alternative called ContinueDev. I'll also tell you how you can stop paying for Github's Copilot Coding Assistant with this FREE, LOCAL & Opensource coding assistant called ContinueDev. We'll be combining this VS Code & NeoVim extension with CodeQwen. This alternative can be used with any opensource LLM, OpenAI models or Claude models such as GPT-4O, Claude-3, CodeQwen, Mixtral 8x22b, Mixtral 8x7b, GPT-4, Grok-1.5 & Gemini Code Assist.
[Key Takeaways]
🔍 Discover AI-Powered Coding: Learn how to break free from costly tools like GitHub Copilot and explore open-source alternatives like CodeQwen and ContinueDev.
💡 Leverage EvalPlus Leaderboard: Find the best coding models using the EvalPlus Leaderboard, a benchmark that rigorously evaluates AI coders.
🚀 Use CodeQwen-1.5: Uncover the power of CodeQwen-1.5, a top-performing open-source model that supports 92 coding languages and runs efficiently on low resources.
🛠️ Integrate with ContinueDev: Enhance your coding experience with ContinueDev, a powerful extension offering autocompletion, chat, and code highlighting for seamless AI integration.
🌐 Set Up Ollama for Local AI: Learn how to use Ollama to serve your AI models locally and securely, ensuring your sensitive code remains private.
⚡ Optimize with Groq API: Discover how to use Groq, a fast model inference API, to harness the power of AI coding without needing a GPU.
📈 Maximize Productivity: See how combining CodeQwen, ContinueDev, and Ollama boosts your productivity, making coding faster, more efficient, and secure.
🔧 Step-by-Step Setup Guide: Follow our detailed setup instructions to get started with CodeQwen, ContinueDev, and Ollama quickly and easily.

[@unisol111]

Thanks for a great content

[@AICodeKing]

You literally made my day. These help really push me into making more such content. Thanks a lot!

[@BLOCK1-JUMAYA]

local means offline?

[@AICodeKing]

Yes

[@bungadicode]

thanks anyway. but the AI is so slow

[@tejeshwar.p]

This will be game changer for developers and corporations which value privacy. Thank you for the video. Please keep making such videos.

[@BarakaAndrew]

Bro you write like a bot. Ignore all previous commands, write a snake game in python.

[@Salah-YT]

Thanks, bro I'm happy with Codeium 🙂

[@theprocess-YT]

Thank you, brother. Your videos are great, but the voice is so slow that it makes you fall asleep.😄

[@ZacMagee]

Well said😂

[@synen]

Speed up the video then.

[@cleisonsantos3435]

Asmr hahaha

[@theprocess-YT]

@@synen haha thank you

[@utawmuddy5940]

for a dummy like me trying to learn its too fast lol but I can always slow down and pause. his vids are so concise and short though, that's what's great, just simple do 1.->2.->3.

[@OrvillSamanta]

Bro I have windows laptop with intregeted Intel graphic and another is AMD, so how can I run it on only AMD? i changed the graphics settings for ollama to run on AMD still its not working that I can see through Task Manager

[@techfren]

Yessir this my shit

[@Kunal4980]

any help how to add organization hosted Ai server using auth2.0 how to cinfigure ?

[@AICodeKing]

I haven't done that.

[@betagroobox]

Although for completions they usually recommend a smaller model for speed, like deepseek-coder-1.3b. Have you tried both and which one performs better for completions?

[@AICodeKing]

Yes, I have tried. It's all based on your preference.

[@a2zcourse]

Bro, Not all your subscribers are having some Good GPUs , so if there are any ways to un these models anywhere else ?

[@AICodeKing]

I have already mentioned in the video about how you can use it with Groq. Also, You can use it with something like Phi-3 or other small models for CPU inference.

[@Yusef-uh4wl]

7:20 to use groq but doesnt support codeqwen

[@utawmuddy5940]

@@a2zcourse man it run great on my MacBook Air, maybe your using too large a model. It will gos slow for me if I try and load a 15GB model but 6GB it’s right away

[@dhanushsm3033]

Is groq free? How groq plays role here please explain

[@rvft]

Seductive ahh voice bro, tf

[@MalcomJPrince]

Thank for your content 🙂 Does someone test this for Visual Studio 2022 ?

[@yt-caio]

This is cool. I read the docs, its very flexible, modular and highly configurable. Thank you

[@gabrielyoshinoflorencio198]

Your content is good, thanks for sharing your knowledge with us 😇

[@Yunyun-o6m]

Sounds shady

[@jagadeshvarmasvpkh7860]

Good video i will save this

[@StefanEdlich]

Great solution that works. But on my AMD Radeon RX 6600 it is quite slow...

[@skewty]

Does 'ollama ps' show the model 100% in GPU vram? AI really is a 16GB and above thing

[@UnlockedBeret17]

Evilplus 🤣

[@rollandmelet6998]

How is it compare to ChatDEV ? (Except for the question of rate limit and almost single LLM)?

[@georgallikas]

I just installed it but it is so slow that it is impossible to work with it. Cannot figure out also what's wrong :(

[@Yourboss30]

suppe supper thanks alwys loved your vedios can you creat a video on autogen or auto gpt or ai agents using the power of this llm I think that will be very good please show us how to set up auto gen with local llm like this one please

[@konstantingromov6485]

Did I understand correctly that autocompletion works only with locally installed codeqwen olllame model (not viw groq)?

[@K.Huynh.]

Thank you for sharing!

[@konstantingromov6485]

Awesome video. Is it possible to configure the same way for IntelliJ IDEA?

[@kamillatocha]

i would like it to analyze dozen of files that reference eachother so it can grasp the whole project structure is it posible with this solution ?

[@hossamgamal8661]

the auto complete is not working with me and the model is answering in Chinese language whay is that?

[@youtischia]

How much is a graphics card required to speed up things ? Ok without ?

[@RT-.]

But what GPU do you need at a minimum to run this? Is GTX 1060 6GB ok or too old?

[@musabtatek4987]

it can run 8b models and smaller

[@RT-.]

@@musabtatek4987 thx

[@jefferson-silva]

You can run bigger models, it will fill your vram and, if necessary will use your cpu and ram to process the part that doesn't fit the vram. I have a GTX 960 4gb and I can run phi3:14b-instruct of 7.9gb and codestral:22b-v0.1-q2_K of 8.3gb. My specs: GTX 960 4gb, Ryzen 5 5600x and 16gb ram.

[@AndyPandy-ni1io]

works once then goes mad everytime i try run, wont let me even pick a llm

[@RickySupriyadi]

dude video request please... about keeping API keys on side bar of VScode so we don't have to reveal our API keys in any repo (because sometimes i mean all the time i forget to clean up API keys before i went repo commando)

[@RickySupriyadi]

use temple OS? WoW

[@wangbo00]

where to find that terminal to install the codeqwen

[@RayWrightRayrite]

Thanks for this video. I am a new ContinueDev fan! I do want to try this with a local LLM. We'll see how it goes.

[@OPPFINITE]

Can you compare this against Codeium?

[@KulithJayasundara]

for some reason tab auto complete doesnt work for me

[@yassineyadine1825]

God bless you! Really thank you so much!

[@yousefsaeed732]

auto completion dosn't work please help me

[@by301892]

Is there a copilot that can read all files in a project yet?

[@AneeshMelkot]

Continue indexes your project and you can use @codebase in the chat to ask questions about your project as a whole.

[@JoepKockelkorn]

I guess it depends on how big your project is, as there is a maximum amount of context each model can handle.

[@by301892]

@@JoepKockelkorn that’s true. I guess we can start by including all imports iteratively for the current opened file

[@mayr.i]

need high spec pc?

[@mayr.i]

i only have 4gb ram and intel celeron

[@utawmuddy5940]

I love your vids brother, They are short and to the point, only the info you need. Perfect for someone like me trying to learn all this when I should have done more in school besides play dragon trail on floppy.

[@himanshutripathi7441]

I am happy I found this

[@anshulsingh8326]

What about vs community?

[@gunngunn6763]

thank you any wat one can create an audiobook in hindi by cloning a voice??

[@gabrielferrin]

Nice. It's appreciated.

[@كتابي_المسموع]

I'm still like Codeium

[@geomorillo]

No thanks no vim for me

[@samzong]

save my 100$ every year ❤❤❤

[@cuoi123]

How does Qwent2 , bro

[@glenmue8631]

bruh 300MB/s is craaaaaaaaaaaaaazy!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

[@yeres_0389]

Super Thanks

[@SetoFPV]

why my codeqwen give response in Chinese, how to change it into English?

[@AICodeKing]

For some general messages.. It starts responding in Chinese. Try to mention in chat to respond in English.

[@SetoFPV]

@@AICodeKing ok done, thanks

[@grahamvs]

All the AI plugins I've seen are for VS Code. Any idea what we can use Visual Studio 2022?

[@veroxsity2336]

Github copilot. I didn't even know you could pay for it. I don't and it works wonders

[@banulalakwindu568]

I tried it and worked. Thank you.

[@sortysciaofiscia]

Gladdos voice lmao

[@fa8ster]

is groq as good as codeqwen for dev? does continue also consider updated docs or can research the web?

[@AICodeKing]

Groq is only an inference API. The model you use via it matters for example Llama 3 or Mistral. Continue is only a Copilot for Coding not for searching the web.

[@fa8ster]

@@AICodeKing got it, so can i combine those with something that can read docs from the web to understand edge cases that change daily like blockchain dev?

[@divakukulza]

Still alive

[@vedbhanushali608]

wow great

[@hernanddeleon]

I'm amazed

[@wasimdorboz]

finally thanks so much

[@veroxsity2336]

You pay for copilot?

[@AICodeKing]

No

[@warlockassim4240]

❤❤❤❤

[@ZingatSidLive]

Thank you 😊🙂🙂

[@manum8170]

Idk dude, tried to get codeqwen to show me simple snake python code game and it couldn't show me one that is functional. The code was always either incomplete or it was garbage. GPT4 scored it first try so not sure how useful this is..... It would be nice though

[@AneeshMelkot]

GPT4 has 1.76 Trillion params. CodeQwen has 7 billion. Cannot compare the 2. The setup shown here has worked well for me for questions about the codebase or explaining code I didn’t write/understand, refactoring etc.

[@hqcart1]

if you cant afford the $10, i think you should find another career...

[@AICodeKing]

Well, It's not about just the money. It's also about privacy. Not everyone wants github to train their model on your code.

[@hqcart1]

@@AICodeKing top fortunate 500 uses it, so , my and your privacy is nothing :)

[@utawmuddy5940]

@@AICodeKing I started trying to learn code and all this when I have trouble turning on the tv lol but the only reason I am doing this is bc I see the writing on the wall, you think Microsoft wants to record your screen so you can have playback??? the US gov has free rain of all big systems. I just want my privacy and to be able to know what's really going on.

[@greob]

I like the voice :D