Prof. Ivan Yamshchikov

ivan-the-bearable's activity

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

upvoted a paper 23 days ago

BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training

Paper • 2409.04599 • Published Sep 6 • 1

upvoted a paper 27 days ago

Toxicity of the Commons: Curating Open-Source Pre-Training Data

Paper • 2410.22587 • Published 29 days ago • 8

upvoted an article 27 days ago

view article

Article

Detoxifying the Commons

By •

27 days ago

• 6