The Kaitchup – AI on a Budget

Phi-4 Multimodal: A Mixture of Audio and Vision LoRA Adapters

The Weekly Kaitchup #81

Don’t Let QLoRA Merging Undo Your Fine-Tuning Work

The Weekly Kaitchup #80

vLLM and Zero-Shot for Low-Cost LLM Evaluation

Mistral Small 3: An Excellent 24B-Parameter Wide-Shallow LLM

The Weekly Kaitchup #79

"Thinking" LLMs with Simple Fine-tuning and Budget Forcing

GRPO: Train LLMs with DeepSeek-R1's Reinforcement Learning Method

The Weekly Kaitchup #78

Qwen2.5-VL: What's New and How Good Are They for Chart and Table Analysis

Fine-Tuning Your LLM to "Think" Like DeepSeek R1, on Your Computer