Evren Ozkip

New video is live!

Explore the Hugging Face ecosystem and learn how to build end-to-end AI apps with LLMs.

https://youtu.be/r477gqo5Oy0

3 weeks ago | [YT] | 7

Evren Ozkip

I’m excited that OpenAI has finally released two open-source models under the Apache 2.0 license.

- The large model runs on a single H100 GPU
- The small model fits within just 16GB of memory

Both are accessible through open-source frameworks like Transformers and Ollama.

I can't wait to build AI apps with these models.

5 months ago | [YT] | 3

Evren Ozkip

AI agents are programs that can autonomously implement a task on behalf of a user. Which AI tool frameworks do you use the most?

10 months ago | [YT] | 2

Evren Ozkip

Meta's new large language model Llama 3 is out. The good news is that you can use this open-source model for free in your own projects.

Llama 3 8B is better than Gemma 7B and Mistral 7B. Llama 3 70B is better than Gemini Pro and Claude 3 Sonnet.

For more information: llama.meta.com/docs/get-started

Skip the Carousel

1 2 3

1 year ago | [YT] | 2

Evren Ozkip

The most used cloud platform is Amazon Web Services (AWS). What is AWS's generative AI service?

1 year ago | [YT] | 11

Evren Ozkip

What is your favorite platform in generative AI❓

1 year ago | [YT] | 0

Evren Ozkip

Amazon Web Services (AWS) is a great cloud platform for AI and machine learning projects.

So which AWS service is used to develop, train, and deploy cloud-based machine learning applications?

2 years ago | [YT] | 4

Evren Ozkip

Which cloud computing platform do you use the most?

2 years ago | [YT] | 1

Evren Ozkip

OpenAI's first-ever developer conference. Here are my some notes from the conference:

1- ChatGPT will now accept not only text but also audio and images.

2- A new GPT-4 Turbo model has been developed.

This model supports tokens up to 128 thousand lengths. This corresponds to approximately 300 pages of a standard book. Previously, this number was 8 thousand, and in some cases 32 thousand.

3- The model will be able to output in JSON format.

4- GPT-4 Turbo has been updated with information until April 2023.

5- GPT-4 Turbo is 3x cheaper than GPT-4 for prompt tokens and 2x for completion tokens. One thousand prompt tokens are $0.01 and one thousand completion tokens are $0.03.

6- Seed parameter was added to fix randomness in the outputs.

7- OpenAI introduced a new Copyright Shield to protect developers and users from potential copyright infringement claims.

In case of a copyright dispute, OpenAI will intervene. If you face legal claims for copyright infringement, OpenAI will pay the costs incurred.

8- The partnership between OpenAI and Microsoft will continue.

9- DALL-E 3: You can integrate DALL-3 into your applications with the Images API by entering the name dall-e-3.

10- Text-to-speech (TTS): You can create human-quality speech with the text-to-speech API. The price is $0.015 per 1000 characters.

11- A new feature called Assistants API has been developed. With this API, you can add agent features to your own applications.

I'm curious about your thoughts on these new announcements.

2 years ago (edited) | [YT] | 7