THUDM/CogView4-6B
Text-to-Image
•
Updated
•
6.84k
•
•
167
C. Emre Karataş
emredeveloper
AI & ML interests
LLM
Recent Activity
liked
a model
2 days ago
THUDM/CogView4-6B
liked
a model
2 days ago
BAAI/bge-reranker-large
liked
a model
2 days ago
tensorblock/DeepSeek-R1-Medical-COT-GGUF
Organizations
None yet
emredeveloper's activity
liked
3
models
2 days ago
liked
a
model
3 days ago
upvoted
an
article
4 days ago
Article
Hugging Face and JFrog partner to make AI Security more transparent
•
18
liked
a
model
5 days ago
upvoted
an
article
5 days ago
Article
A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality
•
57
upvoted
a
paper
6 days ago
liked
2
Spaces
6 days ago
upvoted
a
paper
7 days ago
liked
a
model
8 days ago
upvoted
a
paper
8 days ago
liked
3
models
11 days ago
liked
a
Space
12 days ago
upvoted
an
article
12 days ago
Article
FastRTC: The Real-Time Communication Library for Python
•
130
reacted to
wassemgtk's
post with 🤗🔥
12 days ago
Post
1836
# GESAL: Real-Time Adaptation for LLMs
We’re excited to unveil **Graph-Enhanced Singular Adaptive Learning (GESAL)**, a framework that lets LLMs like
🔗 **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
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.
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).pyNeeds 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.
- 15 replies