23 20 80

Kiran Kamble

kiranr

ki6an

AI & ML interests

nlp,llm

Recent Activity

reacted to wassemgtk's post with 🔥 about 8 hours 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.

new activity 1 day ago

Writer/palmyra-large:Adding `safetensors` variant of this model

authored a paper 15 days ago

Expect the Unexpected: FailSafe Long Context QA for Finance

View all activity

Organizations

kiranr's activity

reacted to wassemgtk's post with 🔥 about 8 hours ago

Post

1058

# 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:

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.