Aleksei Dorkin PRO

adorkin

·

AI & ML interests

Computational Linguistics

Recent Activity

liked a dataset 2 days ago

openeurollm/open-perfectblend-decontaminated

liked a dataset 2 days ago

openeurollm/OpenEuroLLM-Excellent-SFT

upvoted a collection 2 days ago

Index-Translate

View all activity

Organizations

upvoted a collection 2 days ago

Index-Translate

Index‐Translate: A Multilingual Translation Model Family From text & vision to speech, bring meaning across languages • 46 items • Updated 3 days ago • 38

upvoted a collection 4 days ago

GLiClass-v4

The next generation of zero-shot classifiers. • 3 items • Updated 5 days ago • 9

upvoted a changelog 4 days ago

Hugging Face Changelog

Filter Models & Datasets Pages by Author

4 days ago

• 77

upvoted a collection 6 days ago

UltraBERT

UltraBERT: Beyond the Limit of BERT Pre-Training. Pre-trained 150M/380M encoders and a text embedding model, English, 32K context. • 4 items • Updated 7 days ago • 28

upvoted a changelog 7 days ago

Hugging Face Changelog

Faster Tensor Viewer

7 days ago

• 92

upvoted a changelog 8 days ago

Hugging Face Changelog

Contributor permission for access tokens

9 days ago

• 97

upvoted a changelog 12 days ago

Hugging Face Changelog

Decision Models on the Hub

12 days ago

• 226

upvoted a collection 14 days ago

EmbeddingGemma 2

1 item • Updated 15 days ago • 26

upvoted 2 articles about 2 months ago

Article

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

+1

iamleonie, burtenshaw, sergiopaniego

•

Sep 3

• 154

Article

BenchMIRT: What are LLM benchmarks actually measuring?

allenai

•

Sep 1

• 27

upvoted a collection about 2 months ago

Text datasets in French and European languages

11 items • Updated about 24 hours ago • 5

upvoted a collection 2 months ago

🌊 MoM 1.0

long context models for MoM multilingual embeddings • 5 items • Updated Sep 13 • 6

upvoted a collection 3 months ago

Nemotron Supervised Fine-Tuning

SFT datasets covering math, code, chat, safety, agentic, VLM, multilingual, and specialized domains. • 44 items • Updated about 18 hours ago • 22

upvoted a paper 3 months ago

Shieldstral

Paper • 2607.25857 • Published Jul 28 • 23

upvoted a collection 3 months ago

Mage

A family of lightweight multimodal models, including understanding and generation. • 8 items • Updated Jul 26 • 33

upvoted an article 3 months ago

Article

Ulysses Sequence Parallelism: Training with Million-Token Contexts

kashif, stas

•

Mar 9

• 34

upvoted 2 collections 3 months ago

Ettin Rerankers

8 items • Updated May 19 • 11

Bonsai 27B

10 items • Updated Jul 15 • 252

upvoted a changelog 3 months ago

Hugging Face Changelog

Fine-Grained Token Presets

Jul 14

• 73

upvoted a changelog 4 months ago

Hugging Face Changelog

Filter Models page by Hardware

Jun 30

• 228