Writer

Enterprise
company
Verified
Activity Feed

AI & ML interests

AGI, LLMs, Knowledge Graph, Palmyra, Domain Specific LLM

Recent Activity

Writer's activity

wassemgtk 
posted an update 19 days ago
view post
Post
1850
# 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.
·
melisa 
posted an update 7 months ago
view post
Post
3090
🔥 Introducing "Writing in the Margins (WiM)" - better inference pattern for long context LLMs that solves the Lost-in-the-Middle problem 🔥

Paper page: Writing in the Margins: Better Inference Pattern for Long Context Retrieval (2408.14906)

TL;DR
Make your model write "margin notes" as you chunk prefill the KV cache. Then ask it reread all notes before it speaks up.
Works with humans, works with AI 🤖

WiM leverages the chunked prefill of the key-value cache, which concurrently generates query-based extractive summaries at each step of the prefill that are subsequently reintegrated at the end of the computation. We term these intermediate outputs “margins”, drawing inspiration from the practice of making margin notes for improved comprehension of long contexts in human reading. We show that this technique, which adds only minimal additional computation, significantly improves LLMs long context reasoning capabilities.

Think: Every chunk has a chance to be attended to/ be at the end of the context at least once. 🎉

📊 Results:
- An average accuracy boost of 7.5% in multi-hop reasoning tasks like HotpotQA and MultiHop-RAG.
- Even a 30% increase in F1-score for summarisation-like tasks (CWE).

Plus, WiM fits seamlessly into interactive applications (think: progress bar!). It can provide real-time progress updates during data retrieval and integration, making it user-friendly and transparent - a stark contrast to feeding 1mln tokens to an LLMs and waiting 6 min for the first token. 🤯

👩‍💻🧑‍💻 Check it out and contribute to our open-source project here: https://github.com/writer/writing-in-the-margins

🧠 More about chunked prefill: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill
  • 2 replies
·
wassemgtk 
posted an update 11 months ago
view post
Post
3640
Writer team had the opportunity to run an eval for Mixtral-8x22b, results were interesting.

| ---------------------------- |
| #mmlu 77.26 |
| ---------------------------- |
| #hellaswag 88.81 |
| ---------------------------- |
| #truthfulqa 52.05 |
| ---------------------------- |
| #arc_challenge 70.31 |
| ---------------------------- |
| #winogrande 84.93 |
| ---------------------------- |
| #gsm8k 76.65 |
| ---------------------------- |
  • 2 replies
·
wassemgtk 
posted an update about 1 year ago
view post
Post
We are thrilled to announce the release of the OmniACT dataset! This revolutionary dataset and benchmark focuses on pushing the limits of how virtual agents can facilitate the automation of our computer tasks. Imagine less clicking and typing, and more observation as your computer takes care of tasks such as organizing schedules or arranging travel arrangements on its own.

Check it out ➡️ [OmniACT Dataset on Hugging Face]( Writer/omniact)

For a deep dive, here’s the paper: [OmniACT Paper](https://arxiv.org/abs/2402.17553)