Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips
• 10
AI & ML interests
None defined yet.
Recent Activity
Papers
View all Papers Articles
Collection of Unlimited-OCR models.
collection of ERNIE 4.5 models.
-
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text • 30B • Updated • 2.61k • 545 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 59.4k • 794 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 229 • 68 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 569 • • 90
Collection of Unlimited-OCR models.
The serieas of image generation models, including text2img、img2img.
collection of ERNIE 4.5 models.
-
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text • 30B • Updated • 2.61k • 545 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 59.4k • 794 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 229 • 68 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 569 • • 90
Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios.