Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips
•
8
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights.
-
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 1.02k • • 756 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 26 • 60 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 101 • • 69 -
baidu/ERNIE-4.5-300B-A47B-Base-Paddle
Text Generation • 299B • Updated • 61 • 17
collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights.
-
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 1.02k • • 756 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 26 • 60 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 101 • • 69 -
baidu/ERNIE-4.5-300B-A47B-Base-Paddle
Text Generation • 299B • Updated • 61 • 17
Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios.