Hugging Face's logo
Jorge Alonso's picture
1 2 9

Jorge Alonso PRO

oieieio
wassemgtk's profile picture jbisal's profile picture simon-cywang's profile picture
·
https://github.com/OIEIEIO

AI & ML interests

AI/ML

Recent Activity

updated a Space 13 days ago
oieieio/First_agent_template
replied to wassemgtk's post 13 days ago
# GESAL: Real-Time Adaptation for LLMs We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like `meta-llama/Llama-3.2-1B` adapt in real time using user feedback. Check out the code and white paper on GitHub! 🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL) --- ## Why GESAL? Static LLMs struggle to adapt without heavy retraining. GESAL solves this with: - **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters. - **Graph Memory**: Stores adaptations in nodes for scalability. - **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback. --- ## How It Works Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats. --- ## Try It Built with Hugging Face’s `transformers`: ```bash pip install transformers torch numpy python Adaptive_Learning_(GESAL).py ``` Needs a Hugging Face token for Llama-3.2-1B. --- ## Results GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.
replied to wassemgtk's post 13 days ago
# GESAL: Real-Time Adaptation for LLMs We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like `meta-llama/Llama-3.2-1B` adapt in real time using user feedback. Check out the code and white paper on GitHub! 🔗 **Code**: [https://github.com/writer/AI-Adaptive-Learning-GESAL](https://github.com/writer/AI-Adaptive-Learning-GESAL) --- ## Why GESAL? Static LLMs struggle to adapt without heavy retraining. GESAL solves this with: - **SVF**: Adapts weights via \( W' = U (\Sigma \cdot z) V^T \), using few parameters. - **Graph Memory**: Stores adaptations in nodes for scalability. - **RL**: Updates via \( J(z) = \mathbb{E}[\log \pi_z(y|x) r] \) based on feedback. --- ## How It Works Ask "How many R’s in ‘strawberry’?" If it says "2" and you say "no," GESAL learns to say "3" next time, avoiding repeats. --- ## Try It Built with Hugging Face’s `transformers`: ```bash pip install transformers torch numpy python Adaptive_Learning_(GESAL).py ``` Needs a Hugging Face token for Llama-3.2-1B. --- ## Results GESAL hits 95% accuracy after 5 feedbacks vs. LoRA’s 70%. It’s efficient (~0.5M params) and scalable.
View all activity

Organizations

Hugging Face Discord Community's profile picture OIEIEIO's profile picture Lambda Go Labs's profile picture