No Name's picture

No Name

Ainonake

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

RekaAI/reka-flash-3

reacted to tomaarsen's post with ❤️ 6 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!

new activity 11 days ago

Undi95/MistralThinker-v1.1:This shit is fire

View all activity

Organizations

None yet

Ainonake's activity

New activity in Undi95/MistralThinker-v1.1 11 days ago

This shit is fire

#2 opened 18 days ago by

What about finetuning on qwq 32b?

#5 opened 11 days ago by

New activity in yandex/YandexGPT-5-Lite-8B-pretrain 17 days ago

ollama?

#13 opened 18 days ago by

New activity in ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 23 days ago

Translation

#22 opened 23 days ago by

New activity in ValueFX9507/Tifa-Deepsex-14b-CoT about 1 month ago

How to launch this?

#13 opened about 1 month ago by

New activity in anthracite-org/magnum-v4-72b about 1 month ago

You should finetune original R1 671B

#6 opened about 1 month ago by

New activity in Undi95/MG-FinalMix-72B about 2 months ago

Very Very Good

#5 opened about 2 months ago by

New activity in Doctor-Shotgun/L3.3-70B-Magnum-v4-SE about 2 months ago

Magnum manages to impress again

#1 opened about 2 months ago by

New activity in TheDrummer/Moistral-11B-v3-GGUF 2 months ago

Chat template

#5 opened 2 months ago by

New activity in t-tech/T-lite-it-1.0 3 months ago

Отзыв: Гораздо умнее недавно вышедшего гигачата

#5 opened 3 months ago by

New activity in ai-sage/GigaChat-20B-A3B-instruct 3 months ago

Почти сразу начинает повторять себя

#2 opened 3 months ago by

New activity in Sao10K/72B-Qwen2.5-Kunou-v1 3 months ago

Much better than llama 70b

#2 opened 3 months ago by

New activity in ai-sage/GigaChat-20B-A3B-instruct 3 months ago

Признание

#1 opened 3 months ago by

New activity in Sao10K/L3.3-70B-Euryale-v2.3 3 months ago

Fuck "happy"

#2 opened 3 months ago by

New activity in mradermacher/L3.3-70B-Euryale-v2.3-i1-GGUF 3 months ago

Broken files?

#1 opened 3 months ago by

New activity in TheDrummer/Behemoth-123B-v1.2 3 months ago

LOVES to talk as {{user}}

#2 opened 3 months ago by

This model is dangerous 🚨

#3 opened 3 months ago by

New activity in TheDrummer/Endurance-100B-v1 3 months ago

Feedback

#1 opened 3 months ago by

New activity in TheDrummer/Lazarus-2407-100B 3 months ago

Benchmarks?

#4 opened 3 months ago by

Questions

#1 opened 4 months ago by