Instead of showing all new models it is better to implement a single open source llm for all use cases including fine tuning. At the same time it is better to make an end to end project with opensource llm.

Thank You for this video, krish sir.

Thanks sir. Very helpful. Just one question, what's the benefit of Ollama compared with hugging face? I guess it is Local deployed but has some basic requirements for your laptop's hardware.

Hi Krish, Firstly, thanks to your consistent efforts to keep us updated and learn the latest techs in the realm of Data Science. How can I sponsor you on Git Hub and earn a badge?

Hi Krish sir I need a help, please make a video on this basic topic: how ,why to setup virtual environment for python.❤

When using the Llama3 model, sometimes it gives me an incomplete answer. What can I do to avoid incompleteness when generating responses from the Serverless Inference API?

Hey Krish, It will be more helpful if you can take a session on how to use an offline LLM on a custom dataset for QnA

Hi, there will be 10 billion models coming in future and so on..

Hi Krish, thank you for great knowledge you are sharing, I want to run ollama on aws sagemaker, do you know or have any video regarding doing that, I already saw your video to install and work locally, I do not know how to do on the cloud.

Sir, please make a llm video on how to train llm models on custom data.

Hii Krish I too tried the llama3 in ollama response is slow but in your machine the response is fast you are using GPU then what GPU you using ?

Please make a Video on how to finetune LLaMA! I would appreciate it :) Love your videos btw

Is there a way I can use int8 (select specific quantization) for llama3.1 using ollama

Krish i wanted to know what would be the pre requisites to follow your langchain series? How much knowledge do i need?

New models will keep mushrooming every day. I think now videos should focus on more end to end projects using these models. Not just sentiment analysis or language translation or text summarization. Some real life project end to end.

Sir one doubt how much knowledge of dsa is required in data scientist field please clarify

where will those downloaded model files get saved?

can u make video for llama 3 fine-tuning and API creation

do we really need ollama to run llama3. when we are able to download/ clone the entire model from HF, do we still need Ollama for running the model? What is the next step after you download the model from HF? how to use it in the Langchain code without Ollama? is that possible?

Take look at this demo: >>> How many liters of water per minute can a Dutch windmill pump out? That's an interesting question! The answer depends on the specific design and size of the windmill. However, I can give you some general information. Traditionally, Dutch windmills are designed to pump water from shallow sources, such as polders or wells, for irrigation purposes. The capacity of these windmills varies greatly, but a typical small to medium-sized windmill might be able to pump around 0.5 to 2 liters per minute (L/min). Some larger industrial-scale windpumps can pump much more, up to 10-20 L/min or even more, depending on the turbine design and the pressure head of the water. Really? What a sh****

I have ollama on my computer and I am currently using it to run AI models through Python. I need to correct complex instructions that I can only run with the 70B model, the problem is that due to its complexity it takes a long time to execute (2 minutes), how can I lower the times? Currently the model runs on the CPU, how can I configure ollama to use the GPU?

Hi Krish can you please upload a video on Moirai for Time Series LLM Model

sir plzzzzzzzz tell me about this error. RuntimeError: "triu_tril_cuda_template" not implemented for 'BFloat16'

Hello sir, I have a doubt. Is there any platform to find the latest research papers to read? Also, how can I stay updated about the latest developments in the fields of general AI and AI?

When doing Question answering I got an error about logits and LlamaForCausalLM not being compatible, not sure how you got that to work as you said

How can we fine tune llama 3 with a pdf?

This can be fined tune in the same way right?

to run locally which gpu do you use?

How to download llama3 model in local from NVIDIA NIMS? kindly make a video on it please. Thank you

Hi I have a voice model on Google drive but I don't know how to upload it on huggingface can you tell me how to upload it? or giving you the model link and you upload it if you don't mind 😁

Liked your new look, Mr clean.

Bhaiya how do I convert Hindi video into Hindi text, please 🙏 reply much needed ❤

Ye kaam.chatgpt bhi krta hai to ye kyu use kre hum. Llama

Sir how and from where we will get the api key

Dude, don't just copy from hugging face and make a video... try to implement these models on some problem like NER

This guys good.

Sir I'm totally stuck between data field and software field plzz suggest me to overcame from depression 😢😪

my command prompt is raising error saying Ollama not found? any help guys?

Sir please activate neurolab

Ollama is downloading really slow for me, any1 else?

What's app meta ai is awesome 🎉

First Comment 😅

Pair kyu hilaate ho bhai video me

😮

🙏🙂

tanks krish . please answer my email ❤