5 27 51

Celina

celinah

AI & ML interests

inference, on-device and image generation

Recent Activity

reacted to m-ric's post with 🔥 6 days ago

After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: 𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝗠𝗼𝗱𝗲𝗿𝗻𝗕𝗘𝗥𝗧! 🤗 We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models. The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs). It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs. Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub. ➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT. 𝗧𝗟;𝗗𝗥: 🏛️ Architecture changes: ⇒ First, standard modernizations: - Rotary positional embeddings (RoPE) - Replace GeLU with GeGLU, - Use Flash Attention 2 ✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead. 🥇 As a result, the model tops the game of encoder models: It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster! Read the blog post 👉 https://huggingface.co/blog/modernbert

reacted to FranckAbgrall's post with 🔥 6 days ago

🆕 It should now be easier to identify discussions or pull requests where repository owners are participating on HF, let us know it that helps 💬🤗

upvoted a paper 6 days ago

Qwen2.5 Technical Report

View all activity

Organizations

celinah's activity

upvoted a paper 6 days ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published 7 days ago • 328

upvoted an article 28 days ago

Article

Use Models from the Hugging Face Hub in LM Studio

•

28 days ago

• 127

upvoted 2 collections about 1 month ago

🤖 Agents

Collection

21 items • Updated 16 days ago • 57

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 29 days ago • 445

upvoted an article about 1 month ago

Article

The Beginners Guide to Cleaning a Dataset

•

Nov 18

• 24

upvoted an article about 2 months ago

Article

Decoding Strategies in Large Language Models

•

Oct 29

• 38

upvoted a paper about 2 months ago

GPT-4o System Card

Paper • 2410.21276 • Published Oct 25 • 82

upvoted a collection 2 months ago

Open LLM Leaderboard best models ❤️‍🔥

Collection

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 63 items • Updated about 1 hour ago • 484

upvoted 2 articles 2 months ago

Article

Transformers.js v3: WebGPU support, new models & tasks, and more…

Oct 22

• 66

Article

Llama 3.2 in Keras

Oct 21

• 11

upvoted 3 articles 3 months ago

Article

Inference Endpoints Changelog 🚀

•

Oct 11

• 18

Article

Recoloring photos with diffusers

•

Oct 9

• 28

Article

Improving Parquet Dedupe on Hugging Face Hub

Oct 5

• 31

upvoted a paper 3 months ago

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Paper • 2410.02073 • Published Oct 2 • 41

upvoted an article 3 months ago

Article

Llama can now see and run on your device - welcome Llama 3.2

Sep 25

• 180

upvoted an article 5 months ago

Article

XetHub is joining Hugging Face!

Aug 8

• 81

upvoted a paper 6 months ago

ColPali: Efficient Document Retrieval with Vision Language Models

Paper • 2407.01449 • Published Jun 27 • 42

upvoted 3 collections 11 months ago