99
24 728

Gemini 2.0 Flash became ... o1 ? Gemini 2.0 Flash Thinking 🤯

6:49

This new feature of Gemini 2.0 is ... SCARY

6:56

Gemini 2.0 vs GPT4o mini vs Claude 3.5 Haiku ! Gemini did SOOO BAD 😨

11:12

Let's test QwQ, the new opensource alternative to o1

8:20

Llama 3.3 vs Llama 3.2 ! HUGE IMPROVEMENTS !

3:57

Quantization is Simple! Here is how it works

18:47

o1 is dead, long life to o3 ! AGI is CONFIRMED by ARC PRIZE!

Open ai did they 12nd (and last one) announcement.
They released o3, which is a huuuge performance gain.
The performance jump is higher going from o1 to o3 than from GPT4o to o1 !!!
You really have to see the video to fully understand

Відео

Gemini 2.0 Flash became ... o1 ? Gemini 2.0 Flash Thinking 🤯

6:49

Gemini 2.0 Flash became ... o1 ? Gemini 2.0 Flash Thinking 🤯

Переглядів 578День тому

In this video, we are going to take a look at the new Gemini 2.0 Flash Thinking that just released

This new feature of Gemini 2.0 is ... SCARY

6:56

This new feature of Gemini 2.0 is ... SCARY

Переглядів 442День тому

In this video, we are going to take a look at Multimodal Live API with Gemini 2.0 available in aistudio.google.com for free. He is able to hear you, talk to you and see your entire SCREEN !

Gemini 2.0 vs GPT4o mini vs Claude 3.5 Haiku ! Gemini did SOOO BAD 😨

11:12

Gemini 2.0 vs GPT4o mini vs Claude 3.5 Haiku ! Gemini did SOOO BAD 😨

Переглядів 1 тис.14 днів тому

Gemini is reaaally not that great in real use cases. I don't really see why it is ranked so high in the benchmarks

Let's test QwQ, the new opensource alternative to o1

8:20

Let's test QwQ, the new opensource alternative to o1

Переглядів 1,3 тис.21 день тому

In this video, I'm going to test the performances of QwQ, a new preview model released by Qwen that works the same way as o1 from OpenAI

Llama 3.3 vs Llama 3.2 ! HUGE IMPROVEMENTS !

3:57

Llama 3.3 vs Llama 3.2 ! HUGE IMPROVEMENTS !

Переглядів 1,9 тис.21 день тому

Let's compare these two models !

Quantization is Simple! Here is how it works

18:47

Quantization is Simple! Here is how it works

Переглядів 394Місяць тому

In this video, I'm going to show you how quantization is working under the hoods

6:06

BAD vs GOOD prompting

Переглядів 778Місяць тому

Let's see in this video if we still need to make good prompting nowadays and if there is a difference, at what point is it different. Feel free to leave comments, they be negative if they are constructives.

22:09

Is Bigger Better ?

Переглядів 279Місяць тому

In this video, we are going to test the performances of each model size and compare it against other sizes

Qwen2.5 Coder 32B vs GPT4o vs Claude 3.5 Sonnet (new)

14:17

Qwen2.5 Coder 32B vs GPT4o vs Claude 3.5 Sonnet (new)

Переглядів 5 тис.Місяць тому

Let's see which model is the best

Ultimate Guide: Easily Quantize Your LLM in Any Format

3:08

Ultimate Guide: Easily Quantize Your LLM in Any Format

Переглядів 162Місяць тому

Today, I'm going to show you how I quantize all my models : Link : colab.research.google.com/drive/1b6nqC7UZVt8bx4MksX7s656GXPM-eWw4

27:03

New Chinese LLM beat Llama3.2 !!

Переглядів 1302 місяці тому

Let's test a new chinese model and see how it perform against LLama 3.2 and proprieteray models (new Claude 3.5 sonnet, GPT4o)

3:48

Avoir ChatGPT sans Connexion | FR

Переглядів 1852 місяці тому

Bienvenue, Aujourd'hui, je vais vous apprendre à installer une IA locale similaire à ChatGPT.

[Tuto] [FR] | Comment installer et créer une Machine Virtuelle avec VirtualBox (2024)

15:39

[Tuto] [FR] | Comment installer et créer une Machine Virtuelle avec VirtualBox (2024)

Переглядів 4392 місяці тому

Aujourd'hui, je vais vous montrer comment créer vous même des machines virtuels sur votre ordinateur afin que vous ayez un environnement sécurisé et propre