Index ​

Articles ​

LLM ​

• Summarization using the Chain of Density Prompting

• Reduce hallucinations using Chain of Verification CoVe

• Reduce hallucinations in LLM when no content is available

• Parse unstructured text using PyLLMCore

• Generate JSON with Mistral AI Instruct model

• Mistral AI Instruct v0.1 model evaluation in real world use cases

• Implementation of the Toulmin argument: Augmenting argumentation analysis with LLM

Inference ​

• Multi modalities inference using Mistral AI LLaVA vision model - BakLLaVA

• Run Mistral AI inference with llama.cpp

• Inference performance benchmark with llama.cpp

• Enable OpenCL on NUC running Debian

Expert models ​

• Build expert AI models through distillation and parameters pruning

• How to generate a synthetic dataset using a large language model

MacOS - PyObjC ​

• Index your data using MacOS CoreSpotlight and Python

Infrastructure ​

• Manipulate HTTP headers with NGINX

Automation ​

• Automated debian install customization

Content ​

• Generate beautiful charts in Vitepress

• Vectorize PNG : Reduce the color count in the SVG

External resources ​

• Learn how LLM works from scratch : Neural Networks: Zero to Hero - from Andrej Karpathy (OpenAI / Tesla)