AIvatorgo's profile picture. Latest technology information sharing, focusing on AI, full-stack, DevOps technology sharing. Email:flouncy07cheery@icloud.com

AIvator

@AIvatorgo

Latest technology information sharing, focusing on AI, full-stack, DevOps technology sharing. Email:[email protected]

AIvator reposted

🪄 Meet Cali: An AI agent for building React Native apps! Cali can build your project, manage your devices and emulators, help you find and install a library and more... Try Cali today! `npx cali` Powered by @vercel AI SDK. Hacked by me and @o_kwasniewski 💜


AIvator reposted

PuLID for ComfyUI is now live github.com/cubiq/PuLID_Co… (in beta). Please read the README! Also update the IPAdapter if you want to use them together. Thanks to @HclHno3 for converting the weights


AIvator reposted

ComfyUI native IC-Light node is here! github.com/huchenlei/Comf… Really appreciated the great work from @lvminzhang! Cannot wait for the official paper.

HclHno3's tweet image. ComfyUI native IC-Light node is here!
github.com/huchenlei/Comf…

Really appreciated the great work from @lvminzhang! Cannot wait for the official paper.
HclHno3's tweet image. ComfyUI native IC-Light node is here!
github.com/huchenlei/Comf…

Really appreciated the great work from @lvminzhang! Cannot wait for the official paper.

AIvator reposted

BioMistral is a new 7B foundation model for medical domains, based on Mistral and further trained PubMed Central. - top open-source medical Large Language Model (LLM) in its weight class - Apache License - includes base models, fine tunes, and quantized versions.

vanstriendaniel's tweet image. BioMistral is a new 7B foundation model for medical domains, based on Mistral and further trained PubMed Central.
- top open-source medical Large Language Model (LLM) in its weight class
- Apache License
- includes base models, fine tunes, and quantized versions.

AIvator reposted

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy…


AIvator reposted

2023 was a breakout year for AI video. In January, there were no public text-to-video models. Now, there are dozens of video gen products and millions of users. A recap of the biggest developments + companies to watch 👇

venturetwins's tweet image. 2023 was a breakout year for AI video.

In January, there were no public text-to-video models. Now, there are dozens of video gen products and millions of users.

A recap of the biggest developments + companies to watch 👇

AIvator reposted

Day 51 of #60daysOfMachineLearning 🔷 Ensemble Learning 🔷 Ensemble learning is a machine learning technique that combines multiple models to improve the performance and robustness of the final model.

DanKornas's tweet image. Day 51 of #60daysOfMachineLearning

🔷 Ensemble Learning 🔷

Ensemble learning is a machine learning technique that combines multiple models to improve the performance and robustness of the final model.

AIvator reposted

This #GitHub repository (with 100+ case studies) contains everything you need to become proficient in System Design: github.com/Coder-World04/… by @NainaChaturved8


AIvator reposted

🍋 Introducing Wedges — an open source design system & UI component library. A growing collection of Figma + React components (aka Wedges) to help you build your next project faster. The best part? It's completely free. lemonsqueezy.com/wedges


AIvator reposted

PowerInfer can massively speed up inference on consumer GPUs. Almost reaching A100 levels. It outperforms llama.cpp by up to 11.69x while retaining model accuracy. PowerInfer reached an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across…


太酷了

Fine-tuning Mistral 7B with LoRA on a 32 GB M1 (laptop!) in MLX github.com/ml-explore/mlx… Updated example uses less RAM + support for custom datasets 🚀



AIvator reposted

Announcing Mistral 8x7B-*Chat*! A very capable chat model built on top of the new Mistral MoE model, trained on the SlimOrca dataset. Download here: huggingface.co/mattshumer/mis…


AIvator reposted

magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%https://t.co/g0m9cEUz0T%3A80%2Fannounce RELEASE a6bbd9affe0c2725c1b7410d66833e24


AIvator reposted

海外产品开发套件(不定期更新) 做海外产品的开发会让人感到幸福,因为有许多优秀的开发套件——从代码部署到谷歌登录,从订阅收款到分销联盟,都能直接组装使用。 我们可以像搭积木一样,形成一套趁手的研发模板,快速进入业务开发,解决真正的问题。 以下是我正在或计划使用的服务,欢迎推荐补充🧵


AIvator reposted

Bun v1.0.2 - bun --watch gets faster - bunx @latest cache bugfix - Bugfixes to Bun.serve(), node:stream, node:readline, node:tty, transpiller - Concurrent node:fs - v8 date parser - bun run bugfix - urlSearchParams.size, URL.canParse - fastify bugfix bun.sh/blog/bun-v1.0.2


AIvator reposted

Large language models (LLMs) are fun to use, but understanding the fundamentals of how they work is also incredibly important. One major idea and building block of LLMs is their underlying architecture: the decoder-only transformer model. 🧵[1/6]

cwolferesearch's tweet image. Large language models (LLMs) are fun to use, but understanding the fundamentals of how they work is also incredibly important. One major idea and building block of LLMs is their underlying architecture: the decoder-only transformer model. 🧵[1/6]

AIvator reposted

A new ChatPDF.com just dropped - Chats are now saved and can be continued later. This is just the beginning, we have plenty of other improvements in mind, let me know what you'd like to see next!

xathis's tweet image. A new ChatPDF.com just dropped - Chats are now saved and can be continued later.

This is just the beginning, we have plenty of other improvements in mind, let me know what you'd like to see next!

Loading...

Something went wrong.


Something went wrong.