Aleksei Dorkin's picture

Aleksei Dorkin PRO

adorkin

·

slowwavesleep

AI & ML interests

Computational Linguistics

Recent Activity

liked a model 2 days ago

google/gemma-2-2b

liked a model 3 days ago

Qwen/Qwen2.5-Coder-7B

liked a model 6 days ago

microsoft/LLM2CLIP-EVA02-L-14-336

Organizations

adorkin's activity

upvoted a collection 6 days ago

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 7 items • Updated 2 days ago • 35

upvoted an article 7 days ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

8 days ago

• 94

upvoted an article 22 days ago

Article

Decoding Strategies in Large Language Models

By

•

23 days ago

• 38

upvoted a collection 27 days ago

October 25 Releases

19 items • Updated 27 days ago • 7

upvoted 5 collections about 2 months ago

GLiClass

Generalist and Light-weighted Models for Zero-shot Text Classification • 13 items • Updated Sep 17 • 11

Salamandra 🦎

13 items • Updated 14 days ago • 36

Molmo

Artifacts for open multimodal language models. • 5 items • Updated 7 days ago • 271

EuroLLM

2 items • Updated Aug 7 • 15

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 28 days ago • 481

upvoted a collection 2 months ago

Aya Datasets

The Aya Collection is a massive multilingual collection for over 100 languages consisting of 513 million instances of prompts and completions. • 5 items • Updated Jun 28 • 13

upvoted 2 papers 2 months ago

The first neural machine translation system for the Erzya language

Paper • 2209.09368 • Published Sep 19, 2022 • 1

Seamless: Multilingual Expressive and Streaming Speech Translation

Paper • 2312.05187 • Published Dec 8, 2023 • 13

upvoted 2 collections 2 months ago

WebInstruct 🌐 Embeddings 🧱 Models

A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses • 3 items • Updated Sep 4 • 11

Zero-shot Segmentation

6 items • Updated Sep 9 • 4

upvoted 2 papers 3 months ago

Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer

Paper • 2404.04042 • Published Apr 5 • 1

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

Paper • 2408.08872 • Published Aug 16 • 97

upvoted a paper 4 months ago

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12 • 65

upvoted a collection 4 months ago

SAM2

All the models and demos for SAM2 • 8 items • Updated Aug 2 • 12

upvoted a paper 4 months ago

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 85

upvoted a collection 4 months ago

GoLLIE

We present GoLLIE, a Large Language Model trained to follow annotation guidelines that outperforms previous approaches on zero-shot IE. • 4 items • Updated Mar 11 • 18