sometimesanotion

sometimesanotion's activity

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

upvoted 2 collections 3 months ago

GPT-OSS Pruned Experts (4.2B-20B) [IF, Science, Math, etc.]

Collection

Complete collection of domain-specialized GPT-OSS models (1-32 experts) optimized for science, math, medicine, law, safety, and instruction following. • 8 items • Updated Aug 13 • 9

GPT-OSS General (4.2B to 20B)

Collection

Collection of pruned GPT-OSS models spanning 1-32 experts, maintaining general capabilities across domains while reducing computational requirements. • 29 items • Updated Aug 13 • 8

upvoted an article 6 months ago

view article

Article

All LLMs Will Be Sparse BitNet Hybrids

• 

May 14

•

16

upvoted an article 10 months ago

view article

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

• 

Jan 30

•

179

upvoted a collection 11 months ago

Open LLM Leaderboard best models ❤️‍🔥

Collection

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 65 items • Updated Mar 20 • 651

upvoted a paper 12 months ago

Lost in the Middle: How Language Models Use Long Contexts

Paper • 2307.03172 • Published Jul 6, 2023 • 43

upvoted a paper about 1 year ago

Cut Your Losses in Large-Vocabulary Language Models

Paper • 2411.09009 • Published Nov 13, 2024 • 49