1 1 60

Mex Ivanov

MexIvanov

MexIvanov

AI & ML interests

NLP, Coding, Quantum Computing and more.

Recent Activity

reacted to tomaarsen's post with ❤️ 3 days ago

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc. 🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi 3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion ➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common. ⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported. 🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models 📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight. 📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code. Check out the release blogpost here: https://huggingface.co/blog/EuroBERT/release * https://huggingface.co/EuroBERT/EuroBERT-210m * https://huggingface.co/EuroBERT/EuroBERT-610m * https://huggingface.co/EuroBERT/EuroBERT-2.1B The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!

liked a dataset 13 days ago

TuringsSolutions/MemoryVaccine120

liked a model 14 days ago

coqui/XTTS-v2

View all activity

Organizations

None yet

MexIvanov's activity

liked a dataset 13 days ago

TuringsSolutions/MemoryVaccine120

Viewer • Updated 14 days ago • 121 • 66 • 1

liked a model 14 days ago

coqui/XTTS-v2

Text-to-Speech • Updated Dec 11, 2023 • 2.6M • 2.48k

liked a model 23 days ago

Zyphra/Zonos-v0.1-hybrid

Text-to-Speech • Updated 26 days ago • 59.8k • 1.04k

liked a dataset about 2 months ago

DAMO-NLP-SG/multimodal_textbook

Updated Jan 11 • 4.72k • 132

liked a model about 2 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated 9 days ago • 1.58M • 3.65k

liked 2 models 3 months ago

CohereForAI/c4ai-command-r7b-12-2024

Text Generation • Updated 21 days ago • 7.15k • 373

jinaai/jina-embeddings-v3

Feature Extraction • Updated 17 days ago • 2.17M • 817

liked a dataset 3 months ago

wikimedia/wikipedia

Viewer • Updated Jan 9, 2024 • 61.6M • 99.2k • 758

liked a model 4 months ago

NexaAIDev/OmniVLM-968M

Updated Dec 17, 2024 • 1.39k • 513

liked a dataset 8 months ago

HuggingFaceTB/smollm-corpus

Viewer • Updated Sep 6, 2024 • 237M • 12.4k • 311

liked a model 9 months ago

sentence-transformers/LaBSE

liked a dataset 9 months ago

sentence-transformers/trivia-qa-triplet

Viewer • Updated Jun 21, 2024 • 52.9M • 365 • 6

liked 2 models 10 months ago

mistralai/Mistral-7B-v0.3

Text Generation • Updated Jul 24, 2024 • 129k • 445

openbmb/MiniCPM-Llama3-V-2_5

Image-Text-to-Text • Updated Jan 15 • 25k • 1.39k

liked 2 models 12 months ago

urchade/gliner_large_bio-v0.1

Token Classification • Updated Apr 9, 2024 • 147 • 9

urchade/gliner_medium-v2.1

Token Classification • Updated Aug 21, 2024 • 17.6k • 30

liked 4 models about 1 year ago