Oliver Hawthorne's picture

11 41

Oliver Hawthorne

Astris

·

AI & ML interests

None yet

Recent Activity

reacted to lewtun's post with 🔥 7 days ago

I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive! https://x.com/casper_hansen_/status/1875872309996855343 Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025! [1] https://huggingface.co./papers/2412.06769 [2] https://huggingface.co./blog/ganqu/prime

liked a model 12 days ago

deepseek-ai/DeepSeek-V3-Base

liked a model 15 days ago

Qwen/QVQ-72B-Preview

View all activity

Organizations

models 4

Astris/Llama-3-AnySelfMerge

Text Generation • Updated May 16, 2024 • 20 • 1

Astris/ruby-gemma-2b

Text Generation • Updated Mar 9, 2024 • 11

Astris/Furry-AO3-LoRA

Updated Jan 11, 2024 • 1

Astris/Mistral-Adastra-IA3

Updated Oct 4, 2023

datasets 7

Astris/Ensemble_of_models_VQA_v0.5

Viewer • Updated Jul 20, 2024 • 241k • 63

Astris/Nectar-Ranked-DPO

Viewer • Updated Jul 1, 2024 • 503k • 33

Astris/LA-Times

Viewer • Updated Apr 24, 2024 • 3.62M • 41 • 22

Astris/toxic-dpo-v0.2-embedded

Updated Apr 22, 2024 • 33

Astris/lichess-Jan-2013

Viewer • Updated Apr 18, 2024 • 121k • 32

Astris/LA-Times-Linked-Headlines

Viewer • Updated Jan 10, 2024 • 3.72M • 29 • 4

Astris/Nectar-DeDup-Embed

Viewer • Updated Dec 13, 2023 • 1.2M • 40 • 1