PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16 • 93
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16 • 93
Running 4 Doc2Page - Document to Webpage Converter 🏄 4 Convert docs to webpages using PaddleOCR and ERNIE
Sleeping 1 Ernie 4.5 Logprob Compare 🐢 1 Compare the output of ERNIE-4.5-0.3B Instruct and Base model
Sleeping 1 Ernie 4.5 Logprob Compare 🐢 1 Compare the output of ERNIE-4.5-0.3B Instruct and Base model
Sleeping 1 Ernie Embebbing Layer Example 💬 1 Use ERNIE-4.5-0.3B-PT's embedding layer to calc similarity
Sleeping 1 Ernie 4.5 Logprob Compare 🐢 1 Compare the output of ERNIE-4.5-0.3B Instruct and Base model
Sleeping 1 Ernie Embebbing Layer Example 💬 1 Use ERNIE-4.5-0.3B-PT's embedding layer to calc similarity
Sleeping 1 Ernie Embebbing Layer Example 💬 1 Use ERNIE-4.5-0.3B-PT's embedding layer to calc similarity