merve (@mervenoyann) / X

merve

29.6K posts

merve

@mervenoyann

(mer-veh) open-sourceress at @huggingface 🧙🏻‍♀️ DM me for any feedback about HF 🤗 github.com/merveenoyan/sm…

Paris

Joined December 2019

Pinned
merve
@mervenoyann
Jun 11, 2025
I learnt a lot from O'Reilly books, this is surreal I'm writing a book with amazing people @micuelll @andimarafioti @orr_zohar about VLMs with @huggingface 📖💗 Early Access (first two chapters in raw) are available to everyone, we'd love to have your feedback!
181K
merve
@mervenoyann
Oct 2, 2024
solving problems using LLMs that can be solved by fine-tuning BERT is a skill issue
641K
merve
@mervenoyann
Oct 16, 2025
it should be a case study how all AI companies aim for retro aesthetic tbh
Kyle Anthony Miller
@kyleanthony
Oct 15, 2025
Design work lately for B2B AI companies
00:00
189K
merve
@mervenoyann
Jan 27, 2025
people who are baffled by DeepSeek have been and still are sleeping on Qwen, InternLM, ByteDance and Tencent here's couple of fan-favorite models from them 🪭
391K
merve
@mervenoyann
Oct 25, 2024
Microsoft released a groundbreaking model that can be used for web automation, with MIT license 🔥👏 OmniParser is a state-of-the-art UI parsing/understanding model that outperforms GPT4V in parsing. 👏
00:00
473K
merve
@mervenoyann
Aug 5, 2025
we're all sleeping on this OCR model 🔥 dots.ocr is a new 3B model with sota performance, support for 100 languages & allowing commercial use! 🤯 single e2e model to extract image, convert tables, formula, and more into markdown 📝
292K
merve
@mervenoyann
Jan 11, 2024
all the books I accumulated 2 years ago 🫰🏼 most of them I bought myself and 3 of them were gifted by lovely authors 🥹
204K
merve
@mervenoyann
Oct 7, 2024
I'm bullish on this foundation OCR model called GOT 📝 @eccvconf This model can transcribe anything and it's Apache-2.0! Keep reading to learn more 🧶
182K
merve
@mervenoyann
Sep 4, 2024
I was giving consultancy about multimodal RAG to some external people, wanted to post it here stop using OCR + LLMs. if you want to retrieve, use ColPali, if you want RAG from docs, use vision language models
376K
merve
@mervenoyann
Mar 17, 2025
one of the most end-to-end blogs in an applied ML problem someone tried every model available with YOLO and @huggingface transformers to solve signature detection documented their findings and showed how to deploy too
102K
merve
@mervenoyann
Nov 29, 2021
For my midterm I read almost all of the Deep Learning book, until my finals (in two months) I'm writing a very comprehensive blog post that contains my notes and the TF Keras code for each architecture, how (ELI5 maths) and why they work, where to use which 🤓
merve
@mervenoyann
Jun 23, 2025
Hunyuan3D-2.1 passed my in-the-wild test 🤯 insanely good model!
00:00
120K
merve
@mervenoyann
Dec 5, 2024
Welcome PaliGemma 2! 🤗 Google released PaliGemma 2, best vision language model family that comes in various sizes: 3B, 10B, 28B, based on Gemma 2 and SigLIP, comes with transformers support day-0 🎁 Saying this model is amazing would be an understatement, keep reading ✨
167K
merve
@mervenoyann
Oct 9, 2024
I have defended my master's thesis today I have some revisions to make in a month and a whole bureaucracy to tackle but otherwise merged to academia 🤝🏻
94K