Close

Explore AI

Explore GPTs

Explore AI News

Explore AI Videos

Explore AI for Jobs

Latest Scikit-learn AI Videos

Find the latest for scikit-learn company videos

Follow
... 21:15
Best Lightweight Multimodal AI Model: Microsoft Phi-4-Multimodal-Instruct - Install and Run Locally

Aleksandar Haber PhD

1+ months ago 2K views

The video tutorial covers the installation, operation, and applications of the 54 multimodal instruct model developed by Microsoft. This lightweight open-source model handles diverse tasks, including text and audio recognition, image processing, and video analysis. Through example test cases, such as solving a math problem via a sketch and transcribing audio to French, the model's versatility is demonstrated. Instructions for environment setup on Linux, particularly using Nvidia CUDA toolkit for optimization, are provided, along with step-by-step guidance on running the model locally for varying use cases in machine learning and AI fields.
02:29 - 02:39

Instructions for transcribing audio and translating it to French.

Microsoft Machine Learning Research & Innovations
... 4:21
Phi-4 Mini & Multimodal: Microsoft just CRUSHED GPT-4O & Gemini 2.0 Flash!

AISeeKing

1+ months ago 4K views

Microsoft has launched the new 54 mini, a compact multimodal model featuring 3.8 billion parameters and a 128k token context length. Enhanced with supervised fine-tuning and direct preference optimization, it outperforms models like llama 3.23 B and instruct mistol 3B in benchmarks. The 54 multimodal model supports text, image, and audio inputs, offering strong speech recognition capabilities. Both models can be run locally and accessed via platforms like Hugging Face and Nvidia playground. Overall, these advancements underscore a notable shift towards more capable and efficient local AI applications.
02:12 - 02:26

Multimodal model excels in OCR benchmarks against Gemini 2.0 Flash.

Microsoft Natural Language Processing (NLP) AI Trends
... 9:47
How I Would Learn AI as a Software Engineer/Programmer (If I Could Start Over in 2025)

Atef Ataya

1+ months ago 1K views

Learning AI effectively begins with mastering Python and basic math to ensure understanding of underlying principles. Focusing on foundational concepts like regression and classification is crucial before tackling deep learning. Utilizing libraries like Scikit-learn can ease the learning curve through practical projects. Building applications with tools featuring real-world projects showcases acquired skills. Continuous engagement with community and current research helps in staying updated. Ultimately, a structured, hands-on approach, starting from basics to advanced frameworks like large language models, is essential for success in the rapidly evolving AI landscape.
03:17 - 03:47

Interactive, hands-on learning through platforms like DataCamp enriches AI education.

Machine Learning Education
... 7:16
Run Any AI Model Locally On Your Computer!

Astro K Joseph

1+ months ago 1K views

A variety of open source AI models are available for local installation and use. Users can explore models on Hugging Face's platform and easily download them using LM Studio, compatible with Mac, Windows, and Linux. The installation process is straightforward, requiring no advanced configurations or additional dependencies. By searching for specific models like DeepSpeed or LLaMA within LM Studio, users can engage with AI models directly on their machines, experiencing real-time interaction and processing speeds.
04:54 - 05:06

Using LM Studio eliminates the need for installing dependencies to run models.

Machine Learning Tech & Hardware
... 19:30
Easily Create DeepSeek-R1 AI App With GUI and Run Locally on Linux Ubuntu

Aleksandar Haber PhD

1+ months ago 1K views

The tutorial demonstrates how to build a simple desktop application using DeepSeek R1, a reasoning model developed in Python using DEC lama and Streamlit. The audience learns to install the necessary components and create a user-friendly graphical interface for running the AI model locally on a Linux Ubuntu system. The tutorial mentions the capabilities of DeepSeek R1, highlighting its efficiency in solving complex reasoning tasks in mathematics, science, and coding while allowing commercial use under the MIT license. The ease of use of Streamlit for quick AI application development is emphasized.
01:59 - 02:01

Streamlit enables rapid development of interactive AI applications.

Ollama Machine Learning Education
... 15:13
The ULTIMATE Deepseek R1 LOCAL Setup!! 💥 100% Private AI, No Internet 💥

1littlecoder

1+ months ago 6K views

The tutorial presents a local AI setup featuring DeepSeek R1 distilled models, focusing on data privacy by avoiding Chinese data centers. It covers the installation of open-source tools like AMA and Visual Studio Code, demonstrating how to run and utilize distilled models locally. The setup allows secure, non-internet dependent coding assistance and illustrates interactive functionalities through a chat interface for coding queries. The tutorial emphasizes the ease of installation and usability, maintaining data security throughout the process.
04:00 - 04:17

Demonstrates interactive question answering capabilities of the AI model.

Machine Learning Education
... 1:8:27
Build an AI Movie Night Recommendation Tool

DataCamp

1+ months ago 1K views

The session focuses on building a movie recommendation engine using exploratory data analysis and machine learning techniques. It emphasizes the importance of understanding data through visualization and the establishment of a basic recommender system before delving into personalized recommendations using user ratings. The discussion also covers leveraging large language models for enhanced recommendation capabilities. Participants are encouraged to explore the AI-assisted coding environment and gain familiarity with coding methodologies relevant to building effective recommendation systems, increasing engagement with data processing and analysis tasks.
08:29 - 08:50

Details on leveraging user ratings for generating personalized movie recommendations.

Machine Learning Entertainment
... 1:8:27
Build an AI Movie Night Recommendation Tool

DataCamp

1+ months ago 1K views

The session focuses on building a movie recommendation engine using exploratory data analysis and machine learning techniques. It emphasizes the importance of understanding data through visualization and the establishment of a basic recommender system before delving into personalized recommendations using user ratings. The discussion also covers leveraging large language models for enhanced recommendation capabilities. Participants are encouraged to explore the AI-assisted coding environment and gain familiarity with coding methodologies relevant to building effective recommendation systems, increasing engagement with data processing and analysis tasks.
08:29 - 08:50

Details on leveraging user ratings for generating personalized movie recommendations.

Machine Learning Entertainment