Archive - The Kaitchup – AI on a Budget

The Weekly Kaitchup #68

Judge Arena - Fine-Tuning VLMs - Orca AgentInstruct

Nov 22 •

Find the Best LLM for Your GPU

The leaderboards of memory efficiency

Nov 21 •

Black Friday Discounts

30% off for the yearly subscription, a reworked Kaitchup Pro, and the Llama 3.1/3.2 toolbox

Nov 20 •

DPO Full Training vs. LoRA: How Good is LoRA for DPO Training?

One model, two adapters

Nov 18 •

The Weekly Kaitchup #67

Qwen2.5 Coder 32B - Quantization for Models Trained on Large Datasets

Nov 15 •

Fast Inference with GGUF LoRA Adapters on Your CPU

Nov 14 •

Torch Compile: 2x Faster Llama 3.2 with Low Effort

But it will depend on your GPU

Nov 11 •

The Weekly Kaitchup #66

LoRA vs. FFT - Small LM - TRL 0.12.0

Nov 8 •

LLM as a Judge: Evaluate Your LLMs with Another LLM

A good evaluation framework for quick feedback and monitoring

Nov 7 •

Launching AI Toolboxes

First release: Qwen2.5 Toolbox - Llama 3.1/3.2 and open NotebookLM toolboxes will follow

Nov 7 •

Llama 3.2 Embeddings: Training and Evaluation with LLM2Vec

A step-by-step tutorial

Nov 4 •

The Weekly Kaitchup #65

SmolLM2 - Layer Skip - MaskGCT

Nov 1 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts