MergeBench-Llama-8B-it

classroom

AI & ML interests

None defined yet.

Recent Activity

yifeihe3 authored a paper 2 days ago

Semi-Supervised Reward Modeling via Iterative Self-Training

yifeihe3 authored a paper 2 days ago

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

yifeihe3 authored a paper 2 days ago

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

View all activity

MergeBench-Llama-8B-it 's models 5

MergeBench-Llama-8B-it/llama-3.1-8b-it_tulu-3-sft-personas-instruction-following_epoch3_0429

Text Generation • 8B • Updated May 5, 2025 • 3

MergeBench-Llama-8B-it/llama3-8b-it-GRPO-after-sft

Text Generation • 8B • Updated May 2, 2025 • 3

MergeBench-Llama-8B-it/llama-3.1-8b-it_mtl

Text Generation • 8B • Updated May 1, 2025 • 1

MergeBench-Llama-8B-it/llama-3.1-8b-it_aya_2epoch

Text Generation • 8B • Updated Apr 26, 2025 • 3

MergeBench-Llama-8B-it/llama-3.1-8b-it_dart-math-uniform_2epoch

Text Generation • 8B • Updated Apr 25, 2025 • 2