Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips
• 9
AI & ML interests
None defined yet.
Recent Activity
Papers
Measuring Maximum Activations in Open Large Language Models
EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
Articles
The serieas of image generation models, including text2img、img2img.
Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios.
collection of ERNIE 4.5 models.
-
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text • 30B • Updated • 1.43k • 539 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 33k • 786 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • Updated • 48 • 63 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 154 • • 79
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 • 1.43k • 539 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 33k • 786 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • Updated • 48 • 63 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 154 • • 79
Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios.