X / Twitter
Building a search panel for all my Markdown notes:
- Chrome file system API to sync from a directory
- remark to break files into blocks (heading, paragraph, etc)
- mxbai-embed-large model for vector search
- SQLocal to persist
Zero API calls. It's all local 😄 https://t.co/xQY30rKGdD
@jamonholmgren https://t.co/Lgf3D4g0Xn
I wrote myself a Vim cheat sheet for the basic magic: https://t.co/es4FdWlG7r
So I started this journey of reading technical books and it changed my life, from January-August these are the books I have covered, whatever I wanted to learn I googled who are the top authors in that space and read their books
I would love to know what books would you recommend https://t.co/yrIwdCn4V0
Be wary of deep fakes!
PoseTalk is a lip-sync method that can generate talking head videos from a single image, audio, and text prompts.
https://t.co/5FB7KOw8kp https://t.co/c67ASJIky9
my new open-source project
anyone who has played around with PaliGemma, Florence-2 or Qwen-VL knows that the barrier to entry is HIGH
for the past 2-3 weeks, I've been working on a new open-source project that aims to close that gap
link: https://t.co/flnFhxmZXV https://t.co/yoJRfxFvUH
@notmarcoplus Shit is mid stop
Announcing reader-lm-0.5b and reader-lm-1.5b, https://t.co/knzXH6DBr1 two Small Language Models (SLMs) inspired by Jina Reader, and specifically trained to generate clean markdown directly from noisy raw HTML. Both models are multilingual and support a context length of up to 256K tokens. Despite their compact size, these models achieve state-of-the-art performance on this HTML2Markdown task, outperforming larger LLM counterparts while being only 1/50th of their size.
🚨 New powerful open Text to Speech model: Fish Speech 1.4 - trained on 700K hours of speech, multilingual (8 languages)🔥
> Instant Voice Cloning
> Ultra low latency
> ~1GB model weights
> Model weights on the Hub 🤗
> Play with the space in the comments
Kudos to @FishAudio team! They also release a pretty cheap API too 🐐
This summer we went into a hole and rewrote the bulk of Pierre off of RSC and onto a local first sync-engine called Replicache.
It's… really fast. https://t.co/nQuIG8ydpO
congrats to https://t.co/IxPaSONJZp! for everyone else, expand ai at home ;) https://t.co/4NTWT8EKSb
Object Cutter
Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes! https://t.co/9hyYtgZNfJ
They can't see you laugh 😭😭 https://t.co/CSso3oFZCf
Does 3D generation always have to be either slow or complex and data-hungry?🤔 We don’t think so! With Geometry Image Diffusion, we’re all about reusing (and recycling ♻️) what already works — making it faster and easier by reducing complexity and data needs 🚀(1/10) https://t.co/x8HbSSNY0S
MagicSketch 🤩
Interactive image editing Gradio app. 🤯 An MLLM even infers editing intent in real-time and generates a prompt for inpainting for you! https://t.co/VR4hcCAcwC
WebGL Debugging MEGA thread 🔥
Ever since i started WebGL development 10y+ ago I wanted accurate timings of GPU. This was never possible on Mac until now. Turns out you can use Metal Debugger to get detailed peek into everyting under the hood. Read along to find out how. https://t.co/PtajXRXSpB