MergeBench-Llama-3B

AI & ML interests

None defined yet.

Recent Activity

yifeihe3  authored a paper about 12 hours ago

Semi-Supervised Reward Modeling via Iterative Self-Training

yifeihe3  authored a paper about 12 hours ago

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

yifeihe3  authored a paper about 12 hours ago

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

View all activity

Team members 4