NVIDIA NIM Is A Game Changer For Generative AI

[@muratsaglam9671]

Free open source alternative is Ollama

[@Epic-Poetry]

I think NeuralNine has given a demo on Ollama.

How does the cost compare to other similar services?

[@BlackDub21]

Its Nvida, you know its going to be an arm and leg. 😂

@@BlackDub21 As they provide the infrastructure I'm expecting to save an arm.

[@juanbetancourt5106]

Nvidia is not straight with its pricing, but after some clicks, It seems like Nvidia charges you for an anual Enterprise License, its 4.500 usd while other services charges you for tokens (usage) or hours

[@GetBusinessai-i3t]

cool... a code wrapper around using an llm.... the section of your video says "deploy": Question, let's say we use your same example, and used mixtral... how could we actually deploy this to a public IP server (aka a cloud server)?

[@FF-cz8sg]

pre-built means customer can't fine tune the model?

[@flavmusic]

Does it DOWNLOADS the Llama model for instance? Because if it's a about privacy concerns, it's pretty useless if it doesn't download the model itself

[@iamshakeelsindho]

But how can we use Nvidia NIM in RL of our robot Simulation in Isaac Sim? Omniverse and Nvidia Nim structure seems in totally different directions with no clues of how we can use these models and then doing fine-tuning... Any leads?

[@user-wr4yl7tx3w]

can you not do this with Vertex AI also?

[@Epic-Poetry]

To be respectful NVIDIA has kindly sponsored the video

[@amaansamar8401]

I am confused about the GPT 4 deployment on nims. Like it is not an open source model. How is it being hosted in the Nvidia environment. The use of open source models makes sense, like we download it on the system, and we pay for the cost to run it. But gpt4! Did nvidia make a deal with open ai to use there model there model locally. It would be good if it is the case. But if not, then this is just an unnecessary step to use gpt4 from Nims.

[@flavmusic]

It gives a standard API to communicate with.

[@MutairuOnaido]

Nice explanation. Please is there any link to your code?

[@juanbetancourt5106]

Interesting, please consider more content like this, perhaps doing some fine tuning

[@infocascadesoftwaredevelop1661]

how to get a permenant api key

[@NastyGolfer]

This looks like the same thing as AWS Bedrock

[@RobotMegaPower]

I like it greetings from AI Trading

[@siddharth9242]

Is this not free ? It's asking for corporate email Id

[@j.d.4697]

Every single "game changer" now is worth gold on the path to AGI.

[@EliasX962]

cool to see that your using linux

[@cslearn3044]

Bob

[@raghavbansal358]

I came here 2nd

[@alexanderzikal7244]

Terrible what is possible now. Audio, Video, Text,… is 1 thing, in industry KI already working and doing a really good job! Why all Interfaces are focused on python? Keras, Jax,… For some situations C, C++ or Rust would be better

[@adewebs]

I came here first

[@BlackDub21]

I came first then i came over here