159 24 235

Zhe Chen

czczup

https://scholar.google.com/citations?hl=en&user=j1rq_lYAAAAJ

czczup

AI & ML interests

multimodal large language model, vision foundation model

Recent Activity

updated a model 3 minutes ago

OpenGVLab/InternVL2-8B-MPO

new activity about 5 hours ago

OpenGVLab/InternVL2_5-26B-AWQ:Adding `safetensors` variant of this model

new activity about 5 hours ago

OpenGVLab/InternVL2-8B:Update config for T4 Ampere devices

View all activity

Organizations

czczup's activity

updated a model 3 minutes ago

OpenGVLab/InternVL2-8B-MPO

Image-Text-to-Text • Updated 3 minutes ago • 3.16k • 22

New activity in OpenGVLab/InternVL2_5-26B-AWQ about 5 hours ago

Adding `safetensors` variant of this model

#1 opened about 18 hours ago by

SFconvertbot

New activity in OpenGVLab/InternVL2-8B about 5 hours ago

Update config for T4 Ampere devices

#15 opened 4 months ago by

jeanflop

liked a model about 9 hours ago

antphb/Vinqw-1B-v1

Visual Question Answering • Updated 6 days ago • 39 • 5

reacted to BlinkDL's post with 🔥 about 9 hours ago

Post

1004

RWKV-7 "Goose" 0.4B trained w/ ctx4k automatically extrapolates to ctx32k+, and perfectly solves NIAH ctx16k 🤯 100% RNN and attention-free. Only trained on the Pile. No finetuning. Replicable training runs. tested by our community: https://github.com/Jellyfish042/LongMamba