The Kaitchup – AI on a Budget
Subscribe
Sign in
Home
Notes
AI Notebooks
The Kaitchup Pro
The Kaitchup's Book
AI Toolboxes
Tutorials
Models
LLM Leaderboards
Archive
About
DeepSeek-R1: Reinforcement Learning with Simple and Verifiable Rewards
Qwen2.5 and Llama 3.x are good students
Jan 22
•
Benjamin Marie
13
Share this post
The Kaitchup – AI on a Budget
DeepSeek-R1: Reinforcement Learning with Simple and Verifiable Rewards
Copy link
Facebook
Email
Notes
More
2
Local Agentic AI with smolagents and Qwen2.5 Coder
When to use it and when does it fail
Jan 13
•
Benjamin Marie
10
Share this post
The Kaitchup – AI on a Budget
Local Agentic AI with smolagents and Qwen2.5 Coder
Copy link
Facebook
Email
Notes
More
3
DeepSeek-V3: Understanding and Running the Best Open LLM Locally
A huge but efficient MoE
Jan 6
•
Benjamin Marie
14
Share this post
The Kaitchup – AI on a Budget
DeepSeek-V3: Understanding and Running the Best Open LLM Locally
Copy link
Facebook
Email
Notes
More
1
Fine-Tuning Llama 3.3 70B with a Single GPU
And how to fix a poorly accurate 2-bit model
Dec 12, 2024
•
Benjamin Marie
14
Share this post
The Kaitchup – AI on a Budget
Fine-Tuning Llama 3.3 70B with a Single GPU
Copy link
Facebook
Email
Notes
More
Fine-Tune Llama 3.2 Vision, Pixtral, and Qwen2-VL on Your Computer with Unsloth
Step-by-step guide for memory-efficient fine-tuning
Nov 28, 2024
•
Benjamin Marie
9
Share this post
The Kaitchup – AI on a Budget
Fine-Tune Llama 3.2 Vision, Pixtral, and Qwen2-VL on Your Computer with Unsloth
Copy link
Facebook
Email
Notes
More
Most Popular
View all
Multimodal RAG with ColPali and Qwen2-VL on Your Computer
Sep 16, 2024
•
Benjamin Marie
20
Share this post
The Kaitchup – AI on a Budget
Multimodal RAG with ColPali and Qwen2-VL on Your Computer
Copy link
Facebook
Email
Notes
More
11
Fine-tune Llama 3 on Your Computer
Apr 22, 2024
•
Benjamin Marie
11
Share this post
The Kaitchup – AI on a Budget
Fine-tune Llama 3 on Your Computer
Copy link
Facebook
Email
Notes
More
38
QLoRA: Fine-Tune a Large Language Model on Your GPU
May 30, 2023
•
Benjamin Marie
16
Share this post
The Kaitchup – AI on a Budget
QLoRA: Fine-Tune a Large Language Model on Your GPU
Copy link
Facebook
Email
Notes
More
2
DeepSeek-V3: Understanding and Running the Best Open LLM Locally
Jan 6
•
Benjamin Marie
14
Share this post
The Kaitchup – AI on a Budget
DeepSeek-V3: Understanding and Running the Best Open LLM Locally
Copy link
Facebook
Email
Notes
More
1
Latest
Top
Discussions
Fine-Tuning Your LLM to "Think" Like DeepSeek R1, on Your Computer
Experiments with SFT, Llama 3.2 3B, and Training Data Generated by DeepSeek R1
4 hrs ago
•
Benjamin Marie
3
Share this post
The Kaitchup – AI on a Budget
Fine-Tuning Your LLM to "Think" Like DeepSeek R1, on Your Computer
Copy link
Facebook
Email
Notes
More
The Weekly Kaitchup #77
Qwen2.5-VL - Mistral AI and Apache 2.0 - vLLM v1, Janus 7B, and DeepSeek-R1 1.58-bit
Jan 31
•
Benjamin Marie
4
Share this post
The Kaitchup – AI on a Budget
The Weekly Kaitchup #77
Copy link
Facebook
Email
Notes
More
Extract Post-Training Weights as a LoRA Adapter for LLMs
Can we turn DeepSeek-R1 into an adapter?
Jan 30
•
Benjamin Marie
5
Share this post
The Kaitchup – AI on a Budget
Extract Post-Training Weights as a LoRA Adapter for LLMs
Copy link
Facebook
Email
Notes
More
2-bit VPTQ: 6.5x Smaller LLMs, >95% Accuracy
Very accurate 2-bit quantization for running 70B LLMs on a 24 GB GPU
Jan 27
•
Benjamin Marie
6
Share this post
The Kaitchup – AI on a Budget
2-bit VPTQ: 6.5x Smaller LLMs, >95% Accuracy
Copy link
Facebook
Email
Notes
More
3
The Weekly Kaitchup #76
GRPO/TRL - SmolVLM - Coconut
Jan 24
•
Benjamin Marie
8
Share this post
The Kaitchup – AI on a Budget
The Weekly Kaitchup #76
Copy link
Facebook
Email
Notes
More
Estimating Memory Usage for LLMs During Inference (V2)
KV cache, GQA, FlashAttention, activations, batching...
Jan 20
•
Benjamin Marie
7
Share this post
The Kaitchup – AI on a Budget
Estimating Memory Usage for LLMs During Inference (V2)
Copy link
Facebook
Email
Notes
More
6
The Weekly Kaitchup #75
MiniMax-01 - Qwen2.5 PRM - Kokoro and OuteTTS
Jan 17
•
Benjamin Marie
5
Share this post
The Kaitchup – AI on a Budget
The Weekly Kaitchup #75
Copy link
Facebook
Email
Notes
More
MMLU: Do LLMs Really Know?
When 1. = 1. = A. = A. = a. = A) disrupts LLM's world knowledge and language understanding capabilities
Jan 16
•
Benjamin Marie
5
Share this post
The Kaitchup – AI on a Budget
MMLU: Do LLMs Really Know?
Copy link
Facebook
Email
Notes
More
3
The Weekly Kaitchup #74
Open Phi-4 - OLMo 2 Paper
Jan 10
•
Benjamin Marie
5
Share this post
The Kaitchup – AI on a Budget
The Weekly Kaitchup #74
Copy link
Facebook
Email
Notes
More
See all
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.
Subscribe
Recommendations
View all 10
AI Tidbits
Sahar Mor
💎DiamantAI
Nir Diamant
AI Disruption
Meng Li
Generative AI Publication
Jim Clyde Monge
Why Try AI
Daniel Nest
The Kaitchup – AI on a Budget
Subscribe
About
Archive
Recommendations
Sitemap
Share this publication
kaitchup.substack.com
The Kaitchup – AI on a Budget
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts