The MHA2MLA-VLM model published in the paper "MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models"
Xiaoran Fan
cnxup
AI & ML interests
NLP, CV, LLM
Recent Activity
updated
a dataset 22 days ago
cnxup/LLaVA-NeXT-Data published
a dataset about 1 month ago
cnxup/LLaVA-NeXT-Data updated
a model about 1 month ago
cnxup/SVD-Init Organizations
None yet