Ame Vi's picture

6 13

Ame Vi

Ameeeee

·

AI & ML interests

None yet

Recent Activity

reacted to tomaarsen's post with 🔥 1 day 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!

reacted to fdaudens's post with 🔥 13 days ago

Is this the best tool to extract clean info from PDFs, handwriting and complex documents yet? Open source olmOCR just dropped and the results are impressive. Tested the free demo with various documents, including a handwritten Claes Oldenburg letter. The speed is impressive: 3000 tokens/second on your own GPU - that's 1/32 the cost of GPT-4o ($190/million pages). Game-changer for content extraction and digital archives. To achieve this, Ai2 trained a 7B vision language model on 260K pages from 100K PDFs using "document anchoring" - combining PDF metadata with page images. Best part: it actually understands document structure (columns, tables, equations) instead of just jumbling everything together like most OCR tools. Their human eval results back this up. 👉 Try the demo: https://olmocr.allenai.org Going right into the AI toolkit: https://huggingface.co/spaces/JournalistsonHF/ai-toolkit

reacted to burtenshaw's post with 👍 13 days ago

I made a real time voice agent with FastRTC, smolagents, and hugging face inference providers. Check it out in this space: 🔗 https://huggingface.co/spaces/burtenshaw/coworking_agent

View all activity

Organizations

Ameeeee's activity

upvoted an article 15 days ago

Article

Synthetic data: save money, time and carbon with open source

Feb 16, 2024

• 63

upvoted an article 29 days ago

Article

Announcing AI Energy Score Ratings

By

•

29 days ago

• 26

upvoted an article about 2 months ago

Article

Fine-tune ModernBERT for RAG with Synthetic Data

By

and 2 others •

Jan 20

• 37

upvoted an article 4 months ago

Article

Let’s make a generation of amazing image generation models

By

and 4 others •

Nov 26, 2024

• 33