微軟最近開源多模態模型Phi-3-vision-128k-instruct，能處理圖片和文字，且支援128k上下文，應用在圖像辨識(OCR)、圖像理解、資料表分析…等。
微軟最近開源多模態模型Phi-3-vision-128k-instruct，能處理圖片和文字，且支援128k上下文，應用在圖像辨識(OCR)、圖像理解、資料表分析…等。Continue reading on RiCosNote » Read More AI on Medium
#AI
使用ONNX搭配Phi-3-vision模型進行圖像理解
You May Also Like
HITRUST Launches AI Security Assessment with Certification
November 23, 2024
How AI Can Help You Optimize Your Facebook Ads for More Sales
November 23, 2024
A Comprehensive Guide to Spell Checking in Python
November 23, 2024
More From Author
HITRUST Launches AI Security Assessment with Certification
November 23, 2024
How AI Can Help You Optimize Your Facebook Ads for More Sales
November 23, 2024
Realme GT Neo7 is coming next week with a huge battery
November 23, 2024
+ There are no comments
Add yours