Szymon Tworkowski's picture

2 3 26

Szymon Tworkowski

syzymon

·

https://syzymon.github.io

AI & ML interests

Language models, theorem proving and much more!

Recent Activity

authored a paper 7 days ago

Magnushammer: A Transformer-based Approach to Premise Selection

authored a paper 7 days ago

Structured Packing in LLM Training Improves Long Context Utilization

authored a paper 7 days ago

Hierarchical Transformers Are More Efficient Language Models

View all activity

Organizations

None yet

Papers 5

arxiv:2402.13991

arxiv:2312.17296

arxiv:2307.03170

arxiv:2303.04488

models 5

syzymon/long_llama_code_7b_instruct

Text Generation • Updated Oct 6, 2023 • 25 • 11

syzymon/long_llama_code_7b

Text Generation • Updated Sep 24, 2023 • 11 • 31

syzymon/long_llama_3b

Text Generation • Updated Sep 6, 2023 • 88 • 120

syzymon/long_llama_3b_instruct

Text Generation • Updated Aug 5, 2023 • 53 • 25

syzymon/long_llama_3b_v1_1

Text Generation • Updated Aug 4, 2023 • 55 • 10

datasets

None public yet