m0nads

Reasoning without External Rewards

From self-certainty to Reinforcement Learning from Internal Feedback

Jul 20 • 

m0nads

LLMs: a 5 mins trip

What Large Language Models actually do in mathematical terms

Jul 15 • 

m0nads

The Kullback-Leibler divergence

A fundamental comparison tool

Jul 3 • 

m0nads

February 2025

Group Relative Policy Optimization

An efficient and effective reinforcement learning algorithm

Feb 25 • 

m0nads

January 2025

Minimal RAG model

Using Cohere and SerpAPI

Jan 26 • 

m0nads

Byte Latent Transformer

The Efficiency of Dynamic Byte Patching

Jan 14 • 

m0nads

August 2024

Exploring Florence-2

Multimodal AI with Unified Vision-Language Capabilities

Aug 12, 2024 • 

m0nads

June 2024

Covariance and Correlation

Statistical quantities for variables relationships

Jun 17, 2024 • 

m0nads

May 2024

Phi-3 models

Tiny but mighty

May 29, 2024 • 

m0nads

Local RAG using LLaMA3

A quick Retrieval-Augmented Generation model

May 24, 2024 • 

m0nads

Moondream

"A tiny open-source computer-vision model that runs everywhere and kicks ass" (cit.)

May 24, 2024 • 

m0nads

April 2024

JetMoE

LLM training can be much cheaper than people generally thought

Apr 22, 2024 • 

m0nads