tom

roseking

AI & ML interests

maching learning

Recent Activity

posted an update 1 day ago
šŸ“¢ HuggingFace Daily Paper Newsletter (Multilingual) šŸŽÆ Project Link: https://github.com/2404589803/hf-daily-paper-newsletter-multilingual šŸŒŸ What is it? An innovative open-source project that automatically collects the latest AI research papers from HuggingFace and translates them into multiple languages using InternLM-3, making cutting-edge AI research accessible to a global audience! šŸš€ Key Features: - šŸ¤– Automatic daily paper collection from HuggingFace - šŸŒ Supports 5 languages: - šŸ‡ÆšŸ‡µ Japanese - šŸ‡°šŸ‡· Korean - šŸ‡ŖšŸ‡ø Spanish - šŸ‡«šŸ‡· French - šŸ‡¬šŸ‡§ English (original) - āš” Powered by InternLM-3 for high-quality translations - šŸ”„ Daily automated updates via GitHub Actions - šŸ“Š Structured JSON data format - ā° Synchronized with Beijing time (UTC+8) - šŸ“ Complete activity logging šŸ› ļø Technical Stack: - Python - InternLM-3 API - GitHub Actions - requests - pytz - openai - gTTS šŸ”§ Easy Setup: 1. Clone the repository 2. Install dependencies with `pip install -r requirements.txt` 3. Set up your InternLM API key 4. Let GitHub Actions handle the rest! šŸ“‚ Data Organization: - /Paper_metadata_download: Original English papers - /Translated_papers: - /ja: Japanese translations - /ko: Korean translations - /es: Spanish translations - /fr: French translations šŸ¤ Powered By: - [InternLM](https://internlm.org/) - Advanced translation model - [HuggingFace](https://huggingface.co/) - Paper source
replied to their post 15 days ago
šŸŽ‰ Major Updates to HF Daily Paper Newsletter Bot I'm excited to announce significant improvements to my HF Daily Paper Newsletter Bot! Here are the key updates: šŸ–¼ļø Enhanced Poster Generation - Implemented dynamic height adjustment for daily paper posters - Added support for displaying complete paper content without truncation - Improved Chinese font rendering and text layout - Integrated Hugging Face logo for better branding - Enhanced visual aesthetics with optimized card layouts šŸ“ Content Improvements - Removed paper count limitations (previously capped at 5 papers) - Enhanced title and summary extraction algorithms - Improved text wrapping and spacing for better readability - Added proper handling of long content with automatic layout adjustments šŸ› ļø Technical Enhancements - Implemented better font loading mechanism with fallback options - Added support for multiple Chinese font paths - Improved error handling and logging - Enhanced memory management for image processing - Added detailed debugging information šŸŒŸ Visual Design Updates - Refined color scheme with HF brand colors - Improved card spacing and padding - Enhanced typography with better font sizing - Added smooth transitions between paper cards - Optimized overall layout for better visual hierarchy šŸ”§ Infrastructure Updates - Improved GitHub Actions workflow reliability - Enhanced error notification system - Added automatic retries for API calls - Improved logging and debugging capabilities The bot now generates more professional and visually appealing daily paper summaries while ensuring complete content display. These updates make the newsletter more readable and informative for our users. Try it out and let me know what you think! Your feedback helps me make continuous improvements to better serve the AI research community. #HuggingFace #AI #MachineLearning #ResearchPapers #OpenSource
View all activity

Organizations

Stanford AI's profile picture Tsinghua University's profile picture ucas's profile picture Blog-explorers's profile picture ZeroGPU Explorers's profile picture Social Post Explorers's profile picture Chinese LLMs on Hugging Face's profile picture

Posts 6

view post
Post
218
šŸ“¢ HuggingFace Daily Paper Newsletter (Multilingual)
šŸŽÆ Project Link: https://github.com/2404589803/hf-daily-paper-newsletter-multilingual
šŸŒŸ What is it?
An innovative open-source project that automatically collects the latest AI research papers from HuggingFace and translates them into multiple languages using InternLM-3, making cutting-edge AI research accessible to a global audience!
šŸš€ Key Features:
- šŸ¤– Automatic daily paper collection from HuggingFace
- šŸŒ Supports 5 languages:
- šŸ‡ÆšŸ‡µ Japanese
- šŸ‡°šŸ‡· Korean
- šŸ‡ŖšŸ‡ø Spanish
- šŸ‡«šŸ‡· French
- šŸ‡¬šŸ‡§ English (original)
- āš” Powered by InternLM-3 for high-quality translations
- šŸ”„ Daily automated updates via GitHub Actions
- šŸ“Š Structured JSON data format
- ā° Synchronized with Beijing time (UTC+8)
- šŸ“ Complete activity logging
šŸ› ļø Technical Stack:
- Python
- InternLM-3 API
- GitHub Actions
- requests
- pytz
- openai
- gTTS
šŸ”§ Easy Setup:
1. Clone the repository
2. Install dependencies with pip install -r requirements.txt
3. Set up your InternLM API key
4. Let GitHub Actions handle the rest!
šŸ“‚ Data Organization:
- /Paper_metadata_download: Original English papers
- /Translated_papers:
- /ja: Japanese translations
- /ko: Korean translations
- /es: Spanish translations
- /fr: French translations
šŸ¤ Powered By:
- [InternLM](https://internlm.org/) - Advanced translation model
- [HuggingFace](https://huggingface.co/) - Paper source


view post
Post
444
I have an idea that I'm currently working on ā€“ developing a standard API for large models. This standard would ensure compatibility with all known protocols, enabling large models worldwide to be accessed through a unified API. For instance, it could connect models like qwen, deepseek, and GLM from China. However, I haven't found a suitable forum for democratic discussion on this yet. I'm unsure of the next steps. šŸ˜„šŸ˜„šŸ˜„

models

None public yet