Mex Ivanov

MexIvanov
·

AI & ML interests

NLP, Coding, Quantum Computing and more.

Recent Activity

Organizations

None yet

MexIvanov's activity

Reacted to davidberenstein1957's post with 🔥 about 12 hours ago
view post
Post
1582
Let’s make a generation of amazing image-generation models

The best image generation models are trained on human preference datasets, where annotators have selected the best image from a choice of two. Unfortunately, many of these datasets are closed source so the community cannot train open models on them. Let’s change that!

The community can contribute image preferences for an open-source dataset that could be used for building AI models that convert text to image, like the flux or stable diffusion families. The dataset will be open source so everyone can use it to train models that we can all use.

Blog: https://huggingface.co/blog/burtenshaw/image-preferences
Reacted to maxiw's post with ❤️ 14 days ago
view post
Post
4577
I was curious to see what people post here on HF so I created a dataset with all HF Posts: maxiw/hf-posts

Some interesting stats:

Top 5 Authors by Total Impressions:
-----------------------------------
@merve : 171,783 impressions (68 posts)
@fdaudens : 135,253 impressions (81 posts)
@singhsidhukuldeep : 122,591 impressions (81 posts)
@akhaliq : 119,526 impressions (78 posts)
@MonsterMMORPG : 112,500 impressions (45 posts)

Top 5 Users by Number of Reactions Given:
----------------------------------------
@osanseviero : 1278 reactions
@clem : 910 reactions
@John6666 : 899 reactions
@victor : 674 reactions
@samusenps : 655 reactions

Top 5 Most Used Reactions:
-------------------------
❤️: 7048 times
🔥: 5921 times
👍: 4856 times
🚀: 2549 times
🤗: 2065 times
·
Reacted to TuringsSolutions's post with 👀 28 days ago
view post
Post
2888
I have been seeing a specific type of AI hype more and more, I call it, releasing research expecting that no one will ever reproduce your methods, then overhyping your results. I test the methodology of maybe 4-5 research papers per day. That is how I find a lot of my research. Usually, 3-4 of those experiments end up not being reproduceable for some reason. I am starting to think it is not accidental.

So, I am launching a new series where I specifically showcase a research paper by reproducing their methodology and highlighting the blatant flaws that show up when you actually do this. Here is Episode 1!

https://www.youtube.com/watch?v=JLa0cFWm1A4
  • 5 replies
·
Reacted to merve's post with 🤗❤️👍🔥 about 1 month ago
view post
Post
5192
Hugging Face Hub Python library now comes with easy inference for vision language models! ✨

$ pip install huggingface_hub 🤗
  • 1 reply
·
Reacted to singhsidhukuldeep's post with 🔥 about 1 month ago
view post
Post
1169
Good folks from @Microsoft Research have just released bitnet.cpp, a game-changing inference framework that achieves remarkable performance gains.

Key Technical Highlights:
- Achieves speedups of up to 6.17x on x86 CPUs and 5.07x on ARM CPUs
- Reduces energy consumption by 55.4–82.2%
- Enables running 100B parameter models at human reading speed (5–7 tokens/second) on a single CPU

Features Three Optimized Kernels:
1. I2_S: Uses 2-bit weight representation
2. TL1: Implements 4-bit index lookup tables for every two weights
3. TL2: Employs 5-bit compression for every three weights

Performance Metrics:
- Lossless inference with 100% accuracy compared to full-precision models
- Tested across model sizes from 125M to 100B parameters
- Evaluated on both Apple M2 Ultra and Intel i7-13700H processors

This breakthrough makes running large language models locally more accessible than ever, opening new possibilities for edge computing and resource-constrained environments.
  • 4 replies
·
Reacted to AlexBodner's post with 👍 3 months ago
view post
Post
1586
💾🧠Want to know how much VRAM you will need for training your model? 💾🧠
Now you can use this app in which you can input a torch/tensorflow summary or the parameters count and get an estimate of the required memory!
Use it in: howmuchvram.com

Also, everything is Open Source so you can contribute in repo: https://github.com/AlexBodner/How_Much_VRAM
Leave it a star⭐
Reacted to lorraine2's post with 👍🔥 4 months ago
view post
Post
2695
⚡ My PhD thesis, “Scalable Nested Optimization for Deep Learning,” is now on arXiv! ⚡

tl;dr: We develop various optimization tools with highlights, including:
· Making the momentum coefficient complex for adversarial games like GANs.
· Optimizing millions of hyperparameters using implicit differentiation.
· Tuning hyperparameters using hypernetworks.
· Differentiably finding bifurcations in optimization for diverse solutions.

https://arxiv.org/abs/2407.01526
  • 3 replies
·