Tencent/digitalhuman
May 2025 – May 2025
1 Month active
Languages Used
Python
Technical Skills
DebuggingDeep LearningMachine LearningModel DevelopmentModel ImplementationModel Training
mingxiaoli
PROFILE
Mingxiaoli
Worked on the Tencent/digitalhuman repository to enhance deep learning model capabilities by extending the Llava model’s forward method to support labels and text embeddings, enabling more flexible input handling. Introduced a dynamic loss-control mechanism, allowing runtime switching of loss calculation strategies through a new method attribute and setter function. Addressed stability issues by correcting import paths for Llama components and ensuring loss tensor dtype integrity, which improved reliability in the Deepseed training environment. Leveraged Python and expertise in model development, debugging, and natural language processing to deliver these updates, focusing on robust model implementation and seamless integration within the codebase.
Overall Statistics
Feature vs Bugs
33%Features
Repository Contributions
4Total
Bugs
2
Commits
4
Features
1
Lines of code
30
Activity Months1
Your Network
187 peopleSame Organization
@tencent.com179
abushwangMember
LB7666Member
afeizhangMember
AIG-BotMember
aiyiwang2025Member
Hua TianMember
alcheminMember
Jinliang ZhengMember
amintongMember
Shared Repositories
8
Work History
May 2025
4 Commits • 1 Features
May 1, 2025Monthly work summary for 2025-05 for Tencent/digitalhuman focused on delivering core model enhancements, stabilizing training, and improving integration reliability. Key features delivered include extending the Llava model forward to support labels and text embeddings, and introducing a dynamic loss-control mechanism to switch loss strategies. Major bug fixes addressed import path correctness for Llama components and ensured loss dtype integrity during training, enhancing stability in the Deepseed environment.
4 Commits • 1 Features
May 1, 2025Monthly work summary for 2025-05 for Tencent/digitalhuman focused on delivering core model enhancements, stabilizing training, and improving integration reliability. Key features delivered include extending the Llava model forward to support labels and text embeddings, and introducing a dynamic loss-control mechanism to switch loss strategies. Major bug fixes addressed import path correctness for Llama components and ensured loss dtype integrity during training, enhancing stability in the Deepseed environment.
May 2025
Activity
Loading activity data...
Quality Metrics
Correctness85.0%
Maintainability90.0%
Architecture80.0%
Performance70.0%
AI Usage25.0%
Skills & Technologies
Programming Languages
Python
Technical Skills
DebuggingDeep LearningMachine LearningModel DevelopmentModel ImplementationModel TrainingNatural Language Processing
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline