Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips
•
9
AI & ML interests
None defined yet.
Recent Activity
Papers
GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
Articles
Organization Card
Our Mission
At Baidu, our mission is to make the complicated world simpler through technology. We firmly believe that true simplicity is rooted in open source.
🔥 ERNIE 4.5 Model Family Announcement
Affiliated Open Source Organizations
Baidu | PaddlePaddle | ApolloAuto | XuperChain | Baidu AI Cloud
Explore More
collection of ERNIE 4.5 models.
-
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text • 30B • Updated • 4.63k • 512 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 611 • • 770 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 59 • 61 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 127 • • 74
collection of ERNIE 4.5 models.
-
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text • 30B • Updated • 4.63k • 512 -
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation • 22B • Updated • 611 • • 770 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-Paddle
Image-Text-to-Text • 424B • Updated • 59 • 61 -
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text • 424B • Updated • 127 • • 74
Qianfan-vl model series. The models are mainly domain enhanced vision language model, targeting enterprise level multi modal understanding scenarios.
spaces
9
Running
Featured
58
ERNIE-4.5-VL-28B-A3B-Thinking Demo
👐
Compact model, powerful multimodal reasoning.
Running
3
Qianfan VL Demo
💬
Domain-Enhanced Universal Vision-Language Models
Running
17
QuickChat
💬
Quick chat across the ERNIE-4.5 model family.
Running
14
RAG Chat
📚
Ask ERNIE-4.5, grounded in your own knowledge base.
Running
7
ERNIE Web
🤖
Ultra-light web version of ERNIE-4.5 Bot.
Sleeping
9
WebSearch Chat
🌐
Ask ERNIE-4.5, with built-in web search.
models
30
baidu/ERNIE-4.5-VL-28B-A3B-Thinking
Image-Text-to-Text
•
30B
•
Updated
•
4.63k
•
512
baidu/ERNIE-4.5-VL-28B-A3B-PT
Image-Text-to-Text
•
29B
•
Updated
•
120k
•
•
91
baidu/ERNIE-4.5-21B-A3B-Base-PT
Text Generation
•
22B
•
Updated
•
14.8k
•
29
baidu/ERNIE-4.5-VL-28B-A3B-Base-PT
Image-Text-to-Text
•
29B
•
Updated
•
110
•
38
baidu/ERNIE-4.5-VL-424B-A47B-PT
Image-Text-to-Text
•
424B
•
Updated
•
198
•
99
baidu/ERNIE-4.5-300B-A47B-Base-PT
Text Generation
•
299B
•
Updated
•
113
•
•
36
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT
Image-Text-to-Text
•
424B
•
Updated
•
127
•
•
74
baidu/ERNIE-4.5-21B-A3B-Thinking
Text Generation
•
22B
•
Updated
•
611
•
•
770
baidu/ERNIE-4.5-21B-A3B-PT
Text Generation
•
22B
•
Updated
•
19.6k
•
•
162
baidu/ERNIE-4.5-300B-A47B-PT
Text Generation
•
300B
•
Updated
•
186
•
74
datasets
0
None public yet