awascssi's picture

4 69

awascssi

awasm

·

AI & ML interests

None yet

Recent Activity

reacted to aiqtech's post with ➕ 1 day ago

🌐 AI Token Visualization Tool with Perfect Multilingual Support Hello! Today I'm introducing my Token Visualization Tool with comprehensive multilingual support. This web-based application allows you to see how various Large Language Models (LLMs) tokenize text. https://huggingface.co/spaces/aiqtech/LLM-Token-Visual ✨ Key Features 🤖 Multiple LLM Tokenizers: Support for Llama 4, Mistral, Gemma, Deepseek, QWQ, BERT, and more 🔄 Custom Model Support: Use any tokenizer available on HuggingFace 📊 Detailed Token Statistics: Analyze total tokens, unique tokens, compression ratio, and more 🌈 Visual Token Representation: Each token assigned a unique color for visual distinction 📂 File Analysis Support: Upload and analyze large files 🌏 Powerful Multilingual Support The most significant advantage of this tool is its perfect support for all languages: 📝 Asian languages including Korean, Chinese, and Japanese fully supported 🔤 RTL (right-to-left) languages like Arabic and Hebrew supported 🈺 Special characters and emoji tokenization visualization 🧩 Compare tokenization differences between languages 💬 Mixed multilingual text processing analysis 🚀 How It Works Select your desired tokenizer model (predefined or HuggingFace model ID) Input multilingual text or upload a file for analysis Click 'Analyze Text' to see the tokenized results Visually understand how the model breaks down various languages with color-coded tokens 💡 Benefits of Multilingual Processing Understanding multilingual text tokenization patterns helps you: Optimize prompts that mix multiple languages Compare token efficiency across languages (e.g., English vs. Korean vs. Chinese token usage) Predict token usage for internationalization (i18n) applications Optimize costs for multilingual AI services 🛠️ Technology Stack Backend: Flask (Python) Frontend: HTML, CSS, JavaScript (jQuery) Tokenizers: 🤗 Transformers library

liked a Space 2 days ago

openfree/Badge

replied to fantos's post 2 days ago

🎨 BadgeCraft: Create Beautiful Badges with Ease! ✨ Hello there! Today I'm introducing BadgeCraft, a simple app that lets you create stunning badges for your websites, GitHub READMEs, and documentation. 🌟 Key Features 🖌️ 14 diverse color options including vibrant neon colors 🔤 Custom text input for label and message 🖼️ Support for 2000+ logos via Simple Icons 🔗 Clickable link integration 👁️ Real-time preview 💻 Ready-to-use HTML code generation 📝 How to Use Label - Enter the text to display on the left side of the badge (e.g., "Discord", "Version", "Status") Message - Enter the text to display on the right side of the badge Logo - Type the name of a logo provided by Simple Icons (e.g., "discord", "github") Style - Choose the shape of your badge (flat, plastic, for-the-badge, etc.) Color Settings - Select background color, label background color, and logo color Link - Enter the URL that the badge will link to when clicked ✅ Use Cases Add social media links to your GitHub project README Display version information or download links on your website Include tech stack badges in blog posts Show status indicators in documentation (e.g., "in development", "stable") 💡 Tips Click on any of the prepared examples to automatically fill in all settings Copy the generated HTML code and paste directly into your website or blog HTML works in GitHub READMEs, but if you prefer markdown, use the ![alt text](badge URL) format 👨‍💻 Tech Stack This app was built using Gradio and leverages the shields.io API to generate badges. Its simple UI makes it accessible for everyone! 🔗 https://huggingface.co/spaces/openfree/Badge ✨ Available under MIT License - feel free to use and modify.

View all activity

Organizations

None yet

spaces 1

On-Device LLM Throughput Calculator

Generate throughput plot for LLMs

models

None public yet

datasets

None public yet