Bowen Peng

bloc97's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper about 1 month ago

Efficient Pre-Training with Token Superposition

Paper • 2605.06546 • Published May 7 • 46 •

8

New activity in PsycheFoundation/consilience-40b-7Y9v38s5 11 months ago

fixed typo in readme

#1 opened about 1 year ago by

johnpotter

New activity in NousResearch/Nous-Capybara-34B over 2 years ago

How did you train this without going OOM in RAM & VRAM?

3

#15 opened over 2 years ago by

vicplus

New activity in NousResearch/Yarn-Mistral-7b-128k over 2 years ago

VRAM usage for full 128k tokens

7

#5 opened over 2 years ago by

Hypersniper

sliding_window = 131072? Sliding window attention doesn't work for 128?

1

#4 opened over 2 years ago by

keyishen

New activity in NousResearch/Yarn-Llama-2-13b-64k almost 3 years ago

Hardware requirements for the model.

2

#1 opened almost 3 years ago by

Sc0urge