Відео

This is what i want for days.

tested, maybe asking it to do a shooting game is too hard

Don’t to tell me what to do)))))))))

Does the ollama version has the video capability? It can do video on as they said on the hugging face page.

Crystal Loaf

i think it using react native

this is funny you installed the ComfyUI_Qwen2-Audio-7B-Instruct-Int4 node and then procced to show ComfyUI_Qwen2-VL-Instruct node

Interesting. Unfortunately, an application created this way cannot be downloaded as an APK.

thank you!!!!

Good to see some progress on this domain side hopefully this motivates for more high quality products in coming days.. Thanks for sharing

Do you know how to fine tune it? i mean what if i want this model to be trained specialized to recognize birds, all kind of birds... Yes i think it already know birds in general but not specific species. do we can train it with birds images with captions dataset, then after finish training it, whenever a kid wanted to know what birds name she can take picture and ask trained model, then the model will give specific birds name and it's name in biology,

The rise of AI virtual agents is changing the landscape of customer engagement, providing scalable and intelligent solutions. These agents can improve response times, enhance user experiences, and drive operational efficiency

Amazing tutorial thanks! I recommend you add (large language model) to the title to make it more visible in search :)

Ollama could do this already, what is the use for this package?

would you compare this with ColPali?

LM Studio is pretty useless for role-play, and lately Backyard (used to be Faraday) is ridden with bugs now.

PowerShell not recognizing git commands 😢

Hi, thanks for the video. I tried to install Rope-next and the installation is successful. However, when I try to swap the face, I get blurry face. It used to work well for rope main. I have also placed all the models in models folder. Can you help me in case you are aware of this?

It would be really helpful If you could Drop a AI Engineer Roadmap PDF with links to your videos, so that we could easily navigate through it

Johnson Robert Taylor Jennifer Williams Robert

plase, can whispers because i can't and it's my favorite ia ;)

thanks..have you tested the performance upgrade in pandas df with fireduck lib vis-a-vis polars ?..thanks for your reply..

You use terminal always and this puts me off. Please make tutorials with normal gui!

thanks, i likeee soo much :) i hope in two days try to my i7 with 1070gtx (some times pc say 4vram some times say 8vram xD), but today in my i5 poor not nvidia, intel grafics only, in the command cublas i cuda i push OFF but not work, for only cpu some recommendation? :) i dont have avx512 but ollama qwen 1.5 works, gemma2:2b buf, 5 min 1 word aprox jaja

is there a good local host web ui for this? I want to put it on a machine for my nephew to use he's going to school an hour away and I'm getting a bit tired of transcribing his books to audio for him.. ha

How does it compare with sam 2?

not create with modelfile....why?

Ma Shaa Allah, it's really cool 😎

cool video, thanks

I can’t get it to run under linux, it only complains : illegal instruction

Very cool!!

Great interview

can we manual add model? joycaption when we use taggui 1 click installer

hello I upload my model on huggingface can you tell me how to use it?

But if we use streamlit web ui how can we stop the default creation of new run ids?? Also is there any option to delete it?

when i click on 'Live', it is just showing a screen as 'vcam' and my camera is not opening, so what can i do, please help

please review minicpm-v:8b-2.6-fp16 on ollama.

what are the building blocks of ai agents how can I just build one ai agent with specific knowledge base and specific tools to get a job done. I feel like find I can't one video that just answer my question.

Can you use the live as a virtual camera?

Gonzalez Carol Gonzalez Margaret Young Linda

Hi, thank you for making the video about my project, and for your interest.

Please make another video about snorkel explaining how to use it with a big enough data example.

This model is really good. It displays high contextual awareness and the prose is refreshingly good.

Excellent comparison of development tools for AI! SmythOS provides solutions that are easy to use for beginners to assist them get started with AI. #SmythOS #AICoding #TechForBeginners

Right below, gpt-4o-mini, on aider coding benchmark. And better than gemini-1.5-flash-exp-0827.

which model would you recommend of I want to use a model that can read pdf and other file types locally on 12GB of VRAM?

server how go tun nexa server with curl

Would you ever sleep

Thank you for your work 👍 I wonder why people are surprised that the model gets foreign language. The interesting info would be how it handles images.

this occurring continuously step 44000: train loss 1.0522, val loss 1.0794 iter 44000: loss 1.0412, time 1101.20ms iter 44100: loss 1.1706, time 7.81ms iter 44200: loss 1.2474, time 7.82ms iter 44300: loss 1.1227, time 7.80ms iter 44400: loss 1.0755, time 7.82ms iter 44500: loss 1.1175, time 7.81ms iter 44600: loss 1.0708, time 7.83ms iter 44700: loss 1.1190, time 7.81ms iter 44800: loss 1.0835, time 7.83ms iter 44900: loss 1.1040, time 7.81ms