Tong Zhu's picture

Tong Zhu

Spico

·

https://Spico197.github.io

AI & ML interests

Information Extraction, Mixture-of-Experts, LLM

Recent Activity

liked a model 1 day ago

Xiaoye08/HRM-MoE

upvoted a paper 3 days ago

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

upvoted a paper 9 days ago

Draft-OPD: On-Policy Distillation for Speculative Draft Models

View all activity

Organizations

Spico 's models 7

Spico/LLaMA-MoE-v1-2_8-UniformSFT

Text Generation • 7B • Updated Feb 28, 2024 • 8

Spico/LLaMA-MoE-v1-2_8-DynamicSFT

Text Generation • 7B • Updated Feb 28, 2024 • 3

Spico/sheared-llama-2.7b-deita-6k-sft

Text Generation • 3B • Updated Feb 25, 2024 • 6 • 1

Spico/internlm2-7b-hf-llama

Text Generation • Updated Feb 23, 2024 • 3

Spico/mirror-chinese-mrcqa-alpha

Updated Dec 4, 2023

Spico/Humback-Myx

Text Generation • Updated Aug 19, 2023 • 7 • • 3

Spico/Humback-M0

Text Generation • Updated Aug 18, 2023 • 4 • • 3