Your videos get better and better. Most useful focus and very informative. Your focus on the best tools for Local and Private and fine-tuning LLMs is vital content. Patreon donation on its way
Great channel, will you do an instructional video using "LM Studio" and it's local server to host a version of an open source large language model, and then configuring "Open Interpreter" to interact with this local server instead of the OpenAI API key?
First I want to thank for sharing the useful AI content. The LM Studio software was a key step to bring AI assistants a step closer to the customers and consumer. I made use of the software as well and was recently experimenting with dolphin mistral llm 2.2.1 and wondered after a while what the token count 4984/2048 at the bottom right below the chat input means. As far as I understood, it's some sort of counter how many tokens the llm already has written and answered, but why does it matter? Is the chat history fed into the language model each time we enter something new, and this happens somehow behind the scenes? When these language models are working like this, I would understand that the natural limit of the input the language model supports also is the maximum size of the chat history. I am not very familiar with LLM s and just started experimenting with them. Could someone please explain why the token count: yxcd/yxcd number is there and how it affects the Assistants' performance or affect the chat in which way? Thanks in advance
I still have problems to understand the quantization. I know that it have something to do with compression but what do you guys usually download when choosing model files? (I believe I'm not the only one who is confused about all these namings, Q4_K_M, Q3_K_L, Q5_0, Q2_K ... )
Thanks as always for great videos. Could you please possibly look into making a video on LLM quantization (using huggingface or Kagle or any other). The options available (GGUF, GPTQ..etc) and resources required. It is a hot topic. Thanks!
WOw, this looks fantastic. Thank you. I have TextUI but Gradio seems outdated, not as nice looking as this interface. Im really excited about the previous chat section on the left side, like ChatGPT. That will be much easier than TEXTUI where its only in a drop down window.
♦ I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it is just our flesh and that is it. It knows only things of the flesh (our fleshly desires) and cannot comprehend things of the spirit such as peace of heart (which comes from obeying God's Word). Whereas we are a spirit and we have a soul but live in the body (in the flesh). When you go to bed it is your flesh that sleeps but your spirit never sleeps (otherwise you have died physically) that is why you have dreams. More so, true love that endures and last is a thing of the heart (when I say 'heart', I mean 'spirit'). But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons that is a thing of our flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. Take note, love works in conjunction with other spiritual forces such as faith and patience. We should let the Word of God be the standard of our lives not AI. If not, God will let us face AI on our own and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. Our prove text is taken from the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. Let us watch and pray... God bless you as you share this message to others.
Want to connect?
💼Consulting: calendly.com/engineerprompt/consulting-call
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Join Patreon: Patreon.com/PromptEngineering
Your videos get better and better. Most useful focus and very informative. Your focus on the best tools for Local and Private and fine-tuning LLMs is vital content. Patreon donation on its way
Thank you 🙏
The best place to actually understand LLMs and prompting, thanks to this dude i have a job as an AI prompt Engineer tdy. LOVE your videos man.
Thank you 🙏
@@anonforever123 totally real
Great channel, will you do an instructional video using "LM Studio" and it's local server to host a version of an open source large language model, and then configuring "Open Interpreter" to interact with this local server instead of the OpenAI API key?
Looks promising, can't wait this the Linux support comes out of beta.
So does this work regardless of me having a 7900xtx as a gpu and not a nvidia card considering rocm isn't fully ported to windows?
First I want to thank for sharing the useful AI content.
The LM Studio software was a key step to bring AI assistants a step closer to the customers and consumer.
I made use of the software as well and was recently experimenting with dolphin mistral llm 2.2.1 and wondered after a while what the token count 4984/2048 at the bottom right below the chat input means. As far as I understood, it's some sort of counter how many tokens the llm already has written and answered, but why does it matter? Is the chat history fed into the language model each time we enter something new, and this happens somehow behind the scenes? When these language models are working like this, I would understand that the natural limit of the input the language model supports also is the maximum size of the chat history.
I am not very familiar with LLM s and just started experimenting with them. Could someone please explain why the token count: yxcd/yxcd number is there and how it affects the Assistants' performance or affect the chat in which way?
Thanks in advance
I still have problems to understand the quantization. I know that it have something to do with compression but what do you guys usually download when choosing model files? (I believe I'm not the only one who is confused about all these namings, Q4_K_M, Q3_K_L, Q5_0, Q2_K ... )
Thanks as always for great videos. Could you please possibly look into making a video on LLM quantization (using huggingface or Kagle or any other). The options available (GGUF, GPTQ..etc) and resources required. It is a hot topic. Thanks!
WOw, this looks fantastic. Thank you. I have TextUI but Gradio seems outdated, not as nice looking as this interface. Im really excited about the previous chat section on the left side, like ChatGPT. That will be much easier than TEXTUI where its only in a drop down window.
I agree
LOL why are you using fake head ?
On a serious note the problem with LM studio i have is that it is actually CLOSED source, not open source.
yeah why arent more people talkin about the fact that its closed src...
also agree with this point. I think its the limiting factor of the whole thing tbh
So what's the difference between the quality loss settings?
which lm would you choose do google apps scripts?
Do you use SadTalker for the avatar? Does it work for long audio?
Yes, it seems to work for 4-5 minutes but you need something like 3090 with larger vRAM
So how does one select the GPU? It's defaulting to my CPU on all models?
great thank, will be great if you can make a video of (LM Studio API + your LocalGPT) , thank you for great content!
Wow ! Thanks !
Hi, Is there a way to add local files to LM Studio?
It is possible to fine tune the model in lm studio?
I thinks that’s not possible but you can fine tune a model and upload it to hugging face and then use it within LM studio
Thank you 🤩
Thank you 🙏
Which model are you using for the avatar u used in the video?
SadTalker and D-ID
will this help in local documents as knowledge base as well
LM Studio doesn’t have document chat yet, hopefully they will add it sooner
@@engineerprompt There's a plugin for it made by one of the community members in the discord.
@@yorkie4k how is it working? have you tested, can you please share discord channel or link?
The avatar is quite creepy. Ads no value at all to the content.
Not for us, but for him it saves time, may be he is shy and he prefers only recording his voice.
@@recorrthese videos are perfectly fine with just his voice. avatar is not needed at all.
agree@@mbrochh82
hahaha I was thinking the same thing, that "I might kidn@p you " look on his face is creepy as heck
Possible to create embedding studio?
good video
yes, but they really need normal linux support, win 10 was my last windows, only linux after
I agree!
@@engineerprompt yes, PikaOS is my favorite Linux distro, Nvidia ready
Does anyone know the Linux status? It says 'ask on discord'
are you no longer working on LocalGPT?
Updates are coming over the break. Been busy with some stuff but getting back to it soon. Stay tuned
Except it not run on Mac with Intel and else :(
the ai face in the right hand corner is super weird
♦ I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it is just our flesh and that is it. It knows only things of the flesh (our fleshly desires) and cannot comprehend things of the spirit such as peace of heart (which comes from obeying God's Word). Whereas we are a spirit and we have a soul but live in the body (in the flesh). When you go to bed it is your flesh that sleeps but your spirit never sleeps (otherwise you have died physically) that is why you have dreams. More so, true love that endures and last is a thing of the heart (when I say 'heart', I mean 'spirit'). But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons that is a thing of our flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. Take note, love works in conjunction with other spiritual forces such as faith and patience. We should let the Word of God be the standard of our lives not AI. If not, God will let us face AI on our own and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. Our prove text is taken from the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. Let us watch and pray... God bless you as you share this message to others.
When u have an intel MacBook Pro 🥲
u seem much older in your voice hehe
Basically you read the right panel like we all do but you didn't explain anything about their use 😂😂😂😂