The Kaitchup – AI on a Budget

Home
Notes
AI Notebooks
The Kaitchup Pro
The Kaitchup's Book
Tutorials
Models
Archive
About
Fixing Faulty Gradient Accumulation: Understanding the Issue and Its Resolution
Years of suboptimal model training?
 • 
Benjamin Marie
2
Fine-Tuning Meta's Llama 3.2 1B & 3B Models on Budget GPUs
And how they were created
 • 
Benjamin Marie
4
Qwen2.5 QLoRA, LoRA, and Full Fine-tuning on Your Computer
Don't wait for Llama 4 or Qwen3. Qwen2.5 is already a significant progress.
 • 
Benjamin Marie
9
Multimodal RAG with ColPali and Qwen2-VL on Your Computer
Retrieve and exploit information from PDFs without OCR
 • 
Benjamin Marie
11
Run Qwen2-VL on Your Computer with Text, Images, and Video, Step by Step
Your local multimodal chat model
 • 
Benjamin Marie
4
Most Popular
View all
Run Llama 2 70B on Your GPU with ExLlamaV2
 • Benjamin Marie
Fine-tune Llama 3 on Your Computer
 • Benjamin Marie
38
Multimodal RAG with ColPali and Qwen2-VL on Your Computer
 • Benjamin Marie
11
QLoRA: Fine-Tune a Large Language Model on Your GPU
 • Benjamin Marie
The Weekly Kaitchup #63
Fixed Gradient Accumulation - New LLMs by NVIDIA, Zyphra, and Mistral AI
 • 
Benjamin Marie
Train and Serve an AI Chatbot Based on Llama 3.2
Efficient supervised fine-tuning with TRL
 • 
Benjamin Marie
8
Fast Speculative Decoding with Llama 3.2 and vLLM
Boost LLM inference speed with speculative decoding!
 • 
Benjamin Marie
The Weekly Kaitchup #62
Gradient Accumulation - Contextual Document Embeddings - Aria
 • 
Benjamin Marie
7
Generate Synthetic Data from Personas to Train AI Chatbots
Using Personas and Efficient Inference to Create Targeted Training Data for AI Chatbots
 • 
Benjamin Marie
5
Fine-tuning LLMs with 32-bit, 8-bit, and Paged AdamW Optimizers
Finding the right trade-off between memory-efficiency, accuracy, and speed
 • 
Benjamin Marie
5
The Weekly Kaitchup #61
NVLM-D-72B - Whisper Large V3 Turbo - LFM
 • 
Benjamin Marie
The Unreasonable Impact of Gradient Checkpointing for Fine-tuning LLMs
How does gradient checkpointing reduce memory consumption
 • 
Benjamin Marie
2
[Early Access] LLMs on a Budget, Chapter 1: Parameter-Efficient Fine-Tuning
Mastering LoRA
 • 
Benjamin Marie
The Kaitchup – AI on a Budget
The Kaitchup – AI on a Budget
Weekly tutorials, tips, and news on fine-tuning, running, and serving large language models on your computer. The Kaitchup also publishes two new AI notebooks every week.
Recommendations
View all 9
The Poor GPU Guy's Substack
The Poor GPU Guy's Substack
Fabio
Artificial Ignorance
Artificial Ignorance
Charlie Guo
AI Horizon Forecast
AI Horizon Forecast
Nikos Kafritsas
Why Try AI
Why Try AI
Daniel Nest
AI Disruption
AI Disruption
Meng Li

The Kaitchup – AI on a Budget

AboutArchiveRecommendationsSitemap
© 2024 The Kaitchup
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture