Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
1
2
9
Jorge Alonso
PRO
oieieio
Follow
revlon-carter's profile picture
wassemgtk's profile picture
simon-cywang's profile picture
4 followers
·
10 following
https://github.com/OIEIEIO
oieieio1
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
oieieio
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a dataset
29 days ago
Josephgflowers/Finance-Instruct-500k
Viewer
•
Updated
13 days ago
•
518k
•
959
•
40
liked
2 models
2 months ago
microsoft/phi-4
Text Generation
•
Updated
18 days ago
•
505k
•
•
1.9k
lmstudio-community/phi-4-GGUF
Text Generation
•
Updated
Jan 11
•
58.4k
•
44
liked
2 Spaces
2 months ago
Running
on
Zero
291
291
TangoFlux
🚀
Text to Audio (Sound SFX) Generator
Running
on
A10G
1.3k
1.3k
GGUF My Repo
🦙
Create quantized models from Hugging Face repos
liked
a model
2 months ago
IamCreateAI/Ruyi-Mini-7B
Image-to-Video
•
Updated
Dec 25, 2024
•
2.29k
•
604
liked
a model
3 months ago
microsoft/speecht5_tts
Text-to-Speech
•
Updated
Nov 8, 2023
•
185k
•
743
liked
a model
4 months ago
lllyasviel/fav_models
Updated
Jan 28, 2024
•
108
liked
a Space
over 2 years ago
Paused
991
991
Img To Music
🌅