Загрузка видео...

Не удалось загрузить видео

На главную

🆕 How to run (and finetune) open source AI models with a simple API! In 5 mins, I go over how to: ◆ Generate text with DeepSeek R1 & Llama 3 ◆ Generate code with Qwen on LlamaCoder ◆ Generate images with Flux on BlinkShot ◆ Finetune a model...

nutlope's profile picture

Hassan

95,420 subscribers

30,236 просмотров • 1 год назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Mason
Mason1 год назад

Great stuff as usual, btw the Atomic Habits book in the background 🤩

Фото профиля Hassan
Hassan1 год назад

Thanks! Haha yeah I love that book

Фото профиля CodeRabbit
CodeRabbit1 год назад

AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.

Фото профиля Jon
Jon1 год назад

Can you do fine-tuning on vision models to get them to recognize specific people based on input images?

Фото профиля Hassan
Hassan1 год назад

We don't have vision finetuning yet!

Фото профиля Rasheed Well
Rasheed Well1 год назад

All this in 5 minutes! Incredible. Thanks Hassan.

Фото профиля Hassan
Hassan1 год назад

Thanks Rasheed! I'm also working on individual videos where I deep dive into how I built each of my AI apps and explain all the code/architecture.

Фото профиля Vlad
Vlad1 год назад

It can not be easier. Great job!

Фото профиля Hassan
Hassan1 год назад

Thanks!

Фото профиля Manish Sharma
Manish Sharma1 год назад

Hasaan, man crazy good

Фото профиля Hassan
Hassan1 год назад

🙏🙏

Похожие видео

Announcing LlamaCoder v2 – generate React apps in 1 prompt! • Brand new clean conversational UI • New examples & models (e.g Deepseek V3) • Easily iterate & go between versions • High quality mode with LLM chaining 100% free and open source. Powered by Together AI.
0:29

Announcing LlamaCoder v2 – generate React apps in 1 prompt! • Brand new clean conversational UI • New examples & models (e.g Deepseek V3) • Easily iterate & go between versions • High quality mode with LLM chaining 100% free and open source. Powered by Together AI.

Hassan

50,821 просмотров • 1 год назад

Announcing LlamaCoder v3 – generate React apps in 1 prompt! • Multi-file generation for better apps • Monaco editor to view & export code • New models: GLM 4.6, Kimi K2, & Qwen 3 Coder 100% free, open source, and powered by Together AI.
0:34

Announcing LlamaCoder v3 – generate React apps in 1 prompt! • Multi-file generation for better apps • Monaco editor to view & export code • New models: GLM 4.6, Kimi K2, & Qwen 3 Coder 100% free, open source, and powered by Together AI.

Hassan

42,450 просмотров • 7 месяцев назад

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source
0:50

DeepSeek released R1, the best open-source reasoning model that is on par with OpenAI's o1! I have built a RAG app to chat with your PDF files using the DeepSeek R1 model, running locally on your computer. 100% Open Source

Sumanth

678,638 просмотров • 1 год назад

How to launch your own memecoin in seconds using AI? 1) Connect your wallet on: 2) Press generate with AI 3) Tell the AI what memecoin you wanna launch 4) See the magic as it happens Easy, simple & fast $ARENA
1:41

How to launch your own memecoin in seconds using AI? 1) Connect your wallet on: 2) Press generate with AI 3) Tell the AI what memecoin you wanna launch 4) See the magic as it happens Easy, simple & fast $ARENA

Arena.Meme

56,110 просмотров • 1 год назад

Introducing Aura, a chat app for Mac that can do voice-to-text and generate designs. You can speak to any app, use AI models and chat offline. Code mode lets you generate beautiful components, animations, simple sites and share online. It's free with api keys, or with limits.
0:42

Introducing Aura, a chat app for Mac that can do voice-to-text and generate designs. You can speak to any app, use AI models and chat offline. Code mode lets you generate beautiful components, animations, simple sites and share online. It's free with api keys, or with limits.

Meng To

24,279 просмотров • 1 год назад

To generate 3D models in Codex with text-to-cad: Start a new project, write your prompt for a 3D model, and include a link to clone the text-to-cad repo. Codex handles the rest. The repo is open source and all scripts / ui run locally. Link below.
0:21

To generate 3D models in Codex with text-to-cad: Start a new project, write your prompt for a 3D model, and include a link to clone the text-to-cad repo. Codex handles the rest. The repo is open source and all scripts / ui run locally. Link below.

Jake Fitzgerald

22,113 просмотров • 2 месяцев назад

Just built Openjourney 🚀 a vibe coded UI inspired by MidJourney built with Cursor and Replit for you to plug in your favorite models. Generate images with Imagen 4, animate them with Veo 3 or generate videos with sound. Fully open source for you to customize. Links below 👇
2:26

Just built Openjourney 🚀 a vibe coded UI inspired by MidJourney built with Cursor and Replit for you to plug in your favorite models. Generate images with Imagen 4, animate them with Veo 3 or generate videos with sound. Fully open source for you to customize. Links below 👇

Ammaar Reshi

52,820 просмотров • 11 месяцев назад

here's a 39-second tutorial on how to generate meshes with AI (for free!)
0:39

here's a 39-second tutorial on how to generate meshes with AI (for free!)

dylan

26,727 просмотров • 1 год назад

YuE -- Generate Songs from Lyrics on Your PC Locally. [NVIDIA GPU ONLY] Finally an Open Source Alternative to Suno/Udio you can run on your PC. Only 10GB VRAM needed! And you too, can run it on your own PC with this Gradio app, with 1 click. Watch this video (audio on)!
1:04

YuE -- Generate Songs from Lyrics on Your PC Locally. [NVIDIA GPU ONLY] Finally an Open Source Alternative to Suno/Udio you can run on your PC. Only 10GB VRAM needed! And you too, can run it on your own PC with this Gradio app, with 1 click. Watch this video (audio on)!

cocktail peanut

213,280 просмотров • 1 год назад

here's how you can create long-form AI videos in a few seconds and almost $0 budget: - generate your first frame with NanoBanana Pro - generate your voiceover with MiniMax or Elevenlabs - open infinitetalk on runpod (opensource and way cheaper than on official website) - upload your image and voiceover - generate thats it, 2mins and few dollars is all you need to replace $1000s worth of content creators with AI
3:13

here's how you can create long-form AI videos in a few seconds and almost $0 budget: - generate your first frame with NanoBanana Pro - generate your voiceover with MiniMax or Elevenlabs - open infinitetalk on runpod (opensource and way cheaper than on official website) - upload your image and voiceover - generate thats it, 2mins and few dollars is all you need to replace $1000s worth of content creators with AI

MAX

89,076 просмотров • 4 месяцев назад

Announcing MakeComics! Generate custom comics with your own characters and storylines, in seconds. 100% free & open source.
0:21

Announcing MakeComics! Generate custom comics with your own characters and storylines, in seconds. 100% free & open source.

Hassan

81,829 просмотров • 5 месяцев назад

Image generation getting better on Notion. Still need to make it faster, but you can see how you can generate images with prompts, auto-generate cover images and even edit images right inside a doc!
0:49

Image generation getting better on Notion. Still need to make it faster, but you can see how you can generate images with prompts, auto-generate cover images and even edit images right inside a doc!

Akshay Kothari

47,179 просмотров • 4 месяцев назад

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:
0:59

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:

Ruben Hassid

363,453 просмотров • 1 год назад

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:
0:31

🚨BREAKING: OpenAI's Codex is now completely FREE to run locally with Ollama. No API costs. No rate limits. 100% private on your machine. You can now use both the Codex App and Codex CLI with powerful open-source models like DeepSeek V4, Gemma 4, and Qwen 3.6. Here's how to set it up in minutes:

WorldofAI

809,096 просмотров • 1 месяц назад

Meet Houston, your AI data engineer. Run natural language queries with prompt-to-SQL and generate instant charts and dashboards. Build a data pipeline in seconds with our OpenAI chatbot. 🚀#MeetHouston
1:33

Meet Houston, your AI data engineer. Run natural language queries with prompt-to-SQL and generate instant charts and dashboards. Build a data pipeline in seconds with our OpenAI chatbot. 🚀#MeetHouston

Space and Time

141,637 просмотров • 3 лет назад

I just added the new Llama 3.2 1B and 3B models to LitGPT, the open-source LLM library I help develop (focused on efficiency and code readability). LitGPT allows you to fine-tune and use these models on the cloud or a laptop. So, if you are looking for something to play with this weekend: # 1) Finetune the model litgpt finetune_lora meta-llama/Llama-3.2-1B \ --data JSON \ --data.json_path my_custom_dataset.json \ --train.epochs 1 \ --out_dir out/llama-3.2-finetuned \ --precision bf16-true # 2) Chat with the model litgpt chat out/llama-3.2-finetuned/final # 3) Serve the model via an API endpoint litgpt serve out/llama-3.2-finetuned/final
1:48

I just added the new Llama 3.2 1B and 3B models to LitGPT, the open-source LLM library I help develop (focused on efficiency and code readability). LitGPT allows you to fine-tune and use these models on the cloud or a laptop. So, if you are looking for something to play with this weekend: # 1) Finetune the model litgpt finetune_lora meta-llama/Llama-3.2-1B \ --data JSON \ --data.json_path my_custom_dataset.json \ --train.epochs 1 \ --out_dir out/llama-3.2-finetuned \ --precision bf16-true # 2) Chat with the model litgpt chat out/llama-3.2-finetuned/final # 3) Serve the model via an API endpoint litgpt serve out/llama-3.2-finetuned/final

Sebastian Raschka

65,529 просмотров • 1 год назад

Ready to play? AI Playground curates 60+ top open-source AI models for you to explore, experiment, generate images and video, edit, chat, find answers, and more. Plus, it’s easy to use and optimized to run locally on your Intel-powered AI PC. Try it out:
0:52

Ready to play? AI Playground curates 60+ top open-source AI models for you to explore, experiment, generate images and video, edit, chat, find answers, and more. Plus, it’s easy to use and optimized to run locally on your Intel-powered AI PC. Try it out:

Intel

11,304 просмотров • 2 месяцев назад

Introducing Music Finetunes in ElevenCreative. Generate individual vocals, instruments, or full tracks with stylistic consistency using a fine-tuned version of our Music model. Create your own Finetune or get started instantly with 11 Finetunes curated by ElevenLabs.
0:30

Introducing Music Finetunes in ElevenCreative. Generate individual vocals, instruments, or full tracks with stylistic consistency using a fine-tuned version of our Music model. Create your own Finetune or get started instantly with 11 Finetunes curated by ElevenLabs.

ElevenCreative

20,239 просмотров • 4 месяцев назад

Generate Songs with HeartMuLa, with 8GB VRAM! HeartMuLa is the latest open source song generation AI model everyone's raving about. But the default model couldn't run on low VRAM machines. Then WanGP just made it work with just 8GB VRAM! 1-Click Install on Pinokio.
0:47

Generate Songs with HeartMuLa, with 8GB VRAM! HeartMuLa is the latest open source song generation AI model everyone's raving about. But the default model couldn't run on low VRAM machines. Then WanGP just made it work with just 8GB VRAM! 1-Click Install on Pinokio.

cocktail peanut

27,848 просмотров • 5 месяцев назад