Hugging Face's logo
Zixi "Oz" Li's picture
Open to Collab
13 18

Zixi "Oz" Li

OzTianlu
Airin-chan's profile picture 21world's profile picture Layth888's profile picture
Β·
https://github.com/lizixi-0x2F

AI & ML interests

My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.

Recent Activity

updated a collection about 18 hours ago
Geilim Large Language Models
reacted to their post with πŸ”₯ about 18 hours ago
Geilim-1B-SR-Instruct β€” Serbian Intelligence for Deep Reasoning πŸ§ πŸ‡·πŸ‡Έ https://huggingface.co/NoesisLab/Geilim-1B-SR-Instruct Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. πŸš€ Core Innovations πŸ’‘ Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. πŸ•ΈοΈ ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚑ Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍 Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. πŸ’» Use Cases πŸ› οΈ Serbian Chatbots: Intelligent assistants with local linguistic nuance. πŸ—£οΈ Educational Tools: Multi-turn interactive tasks and learning support. πŸ“š Key Advantages ✨ Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. βœ… Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. πŸ”“ AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🀝
posted an update about 18 hours ago
Geilim-1B-SR-Instruct β€” Serbian Intelligence for Deep Reasoning πŸ§ πŸ‡·πŸ‡Έ https://huggingface.co/NoesisLab/Geilim-1B-SR-Instruct Geilim-1B-SR-Instruct is a lightweight Large Language Model (LLM) designed to bring advanced reasoning capabilities to low-resource languages. It focuses on Serbian understanding and generation while maintaining robust English reasoning. Built on the LLaMA-3 architecture with a proprietary hybrid reasoning mechanism, it delivers deep logic while keeping outputs concise and natural. πŸš€ Core Innovations πŸ’‘ Implicit Deep Reasoning: Combines standard attention mechanisms with graph-structured reasoning components for rigorous logic and causal inference. πŸ•ΈοΈ ASPP & -flow Hybrid Design: High-efficiency structured propagation + internal probability space optimization for high-quality reasoning without long-winded intermediate steps. ⚑ Bilingual Adaptation: Primarily focused on Serbian while preserving English logic, making it perfect for multilingual chats and cross-lingual tasks. 🌍 Lightweight & Efficient: At ~1.3B parameters, it runs smoothly on consumer-grade GPUs, ideal for edge devices and research. πŸ’» Use Cases πŸ› οΈ Serbian Chatbots: Intelligent assistants with local linguistic nuance. πŸ—£οΈ Educational Tools: Multi-turn interactive tasks and learning support. πŸ“š Key Advantages ✨ Clean Output: Avoids messy "thinking" tags; reasoning happens internally, delivering clear and direct results. βœ… Open Access: Licensed under Apache-2.0, making it easy for research and engineering integration. πŸ”“ AI Democratization: Empowering low-resource language ecosystems with cutting-edge intelligence. 🀝
View all activity

Organizations

NoesisLab's profile picture