ML Blog

 

Evals are dead. Long live evals!

AI
LLM
Reinforcement Learning
Eval
Agents

deep dive into RL environments and Verifiers

Oct 5, 2025
Anshuman Mishra

Introducing Falafel: AI Video Generation in DaVinci Resolve

SaaS
Diffusion
Video Editing
Open Source

Bringing FalAI to davinci resolve

Aug 11, 2025

Training LLMs to Think

LLMs

Post training a LLM for reasoning with GRPO using Unsloth

Aug 4, 2025

What is GSPO?

LLMs

How does Group Sequence Policy Optimization work?

Jul 27, 2025

Fine-Tuning a Vision Language Model in 2025

VLMs
Fine-tuning

How to fine-tune Gemma3 vision on consumer hardware with 4-bit quantization (QLoRA)

Jul 27, 2025

Building Production Ready Text-to-SQL Agent from Scratch

LLMs
Agents

Tired of Writing SQL? Let’s Build an AI That Does It For You.

Jun 6, 2025

The AI Memory Layer Will Change Everything

LLMs
Agents

How Stateful Memory is Revolutionizing AI Agents and Applications

Jun 3, 2025

Illustrated LLM OS

LLMs
Operating-system

An Implementational Perspective of LLMs as Operating Systems

Dec 3, 2023
 

Generating High-quality Images with SD.Next, HuggingFace Diffusers and W&B

Diffusion
Wandb

A walkthrough of using SD.Next (Advanced webUI for Stable Diffusion) for generating high-quality images using HuggingFace Diffusers and managing experiments with W&B.

Oct 2, 2023
 

Predicting Semantic Similarity using KerasNLP

KerasHub
LLMs
Wandb

This report demonstrates how to use the Weights&Biases to speedup experiments with Keras

Sep 2, 2023

Deep Learning in Julia

Model Architecture
Julia

Implementing ML models in Flux, the Julia Deep Learning Package!

Dec 31, 2022
No matching items