Artificial intelligence
On-premise AI, local language models and enterprise use cases.
-
Running a language model locally: what to measure before buying the machine
Before choosing between a 32-billion and a 72-billion parameter model, you need to know what to measure. Here is the protocol we apply and the orders of magnitude to check on your own hardware.
-
Training your teams in generative AI: the standard three-day programme
Three days are enough to make a business team self-sufficient with generative AI, provided they work on their own tasks. Here is the outline we follow.
-
What machine do you need to run an AI locally?
Video memory decides almost everything. Here is how to size a machine to run a language model on your premises, and how to check for yourself before buying.
-
How do you make an AI answer on your own documents?
A language model does not know your procedures. The method that works is to give it the right extracts at the moment of the question, rather than trying to teach them to it.
-
Teaching a machine to read handwritten documents
Readings filled in by hand on the shop floor end up retyped into a spreadsheet. A vision model can read them — provided it can also say when it did not understand.
-
Artificial intelligence in Algerian industry
Maintenance, quality control, consumption forecasting: the use cases that hold up in a plant are the ones whose data already exists. Here is how to tell them apart.
-
Which open language model should a company choose?
The best model is not the largest, it is the smallest that answers your questions correctly. Here is the method for deciding on your own data rather than on leaderboards.
-
Choosing an AI provider in Algeria: 7 questions
Every provider talks about sovereignty and local deployment. Here are the seven questions that separate those who deliver from those who present.