Zoe Noctilucens

Noctilucens's activity

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

upvoted a collection 3 months ago

OpenChat-3.5-0106 with Additional Layers

Collection

Upscaled models using the Block Expansion method. Unlike the more common DUP Scaling, BE doesn't require fine-tuning to recover lost performance. • 7 items • Updated about 11 hours ago • 2

upvoted an article 3 months ago

view article

Article

Rank-Stabilized LoRA: Unlocking the Potential of LoRA Fine-Tuning

By •

Feb 20

• 15

upvoted a paper 3 months ago

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Paper • 2309.10400 • Published Sep 19, 2023 • 26

upvoted a paper 4 months ago

YaRN: Efficient Context Window Extension of Large Language Models

Paper • 2309.00071 • Published Aug 31, 2023 • 65