Sign in

Rajat Arya

@rajatarya.com
149 followers 96 following 10 posts

HF tech lead + software engineer, previously XetHub co-founder, 10+yrs building ML systems. Personal account, opinions are entirely mine and not any current or former employer. Work account is @rajatarya.hf.co.

PostsRepliesMedia
Rajat Arya @rajatarya.com · 30/07/2025
Built my 1st app exclusively using @hf.co Hub features! It helps me keep track/summarize the latest HF News. Uses Datasets, Inference Endpoints, the newly announced `hf jobs`, and Spaces to visualize results. Check it out here: huggingface.co/spaces/rajat...
Screenshot of running HF News Aggregator.
061
Reposted by Rajat Arya
Dare Obasanjo @carnage4life.bsky.social · 15/05/2025
We are in such a weird place where caring about other people is political.
829946
Rajat Arya @rajatarya.com · 26/06/2025
So much fun to be a part of this team, and at HF in general! 100PB here we come!
010
Rajat Arya @rajatarya.com · 06/06/2025
I regularly forget how powerful locally running LLMs are. Today's example, want to configure your awesome WezTerm but can't bring yourself to read docs/write Lua code. Just have Qwen3 do it for you. I like llama-server best, and download models from HF, from here: github.com/ggml-org/lla...
Screenshot of terminal with cmd line to launch llama-server Qwen3 model from HF. Below terminal is browser window showing llama-server running with the prompt: "Can you help me write config files for WezTerm?"
030
Rajat Arya @rajatarya.com · 29/05/2025
If I listen to 90s music, now that some of it is > 30 years old, does this mean Spotify doesn't pay royalties to the artists? Do royalties stop when copyright ends? (I'm thinking about this as "Mother" by Danzig is playing in the background.)
110
Rajat Arya @rajatarya.com · 05/04/2025
31% Dedupe!
010
Reposted by Rajat Arya
jsulz @jsulz.com · 05/04/2025
The entire Xet team is so excited to bring Llama 4 to the @hf.co community. Every byte downloaded comes through our infrastructure ❤️ 🤗 ❤️ 🤗 ❤️ 🤗 Read the whole post to see more about these models.
huggingface.co
Welcome Llama 4 Maverick & Scout on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
172
Reposted by Rajat Arya
jsulz @jsulz.com · 12/03/2025
It's finally here ❤️ Build faster than ever on @hf.co starting today with 10x better upload/download performance. ⚡ Xet storage is rolling out access across the Hub; join the waitlist now! 🚀
huggingface.co
Join the Xet waitlist · Hugging Face
Unlock 10x faster uploads and downloads on HF
153
Reposted by Rajat Arya
jsulz @jsulz.com · 26/11/2024
On the Xet team at @huggingface.bsky.social we're always looking for ways to move bytes to computer near you as fast as possible. To do this, we're redesigning the upload and download infrastructure on the Hub. This post describes how, check the thread for details 🧵 huggingface.co/blog/rearchi...
huggingface.co
Rearchitecting Hugging Face Uploads and Downloads
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
96611
Rajat Arya @rajatarya.com · 23/11/2024
Could you imagine giving a ⭐-rating to a bridge every time you cross it? Infrastructure - even software infrastructure - is meant to be unsexy & work. It doesn't need Likes, Stars, and Re-posts to measure its impact. It uses adoption and utility to measure its impact.
020
Rajat Arya @rajatarya.com · 21/11/2024
So much fun to work on this with the Xet-team!
020