#other#agent#llm#rag
Happy-LLM is a free, open-source learning project that helps you deeply understand large language models (LLMs) from basics to advanced training and applications. It teaches you key concepts like NLP, Transformer architecture, pretraining, and how to build and train your own LLaMA2 model step-by-step. You also learn practical skills like fine-tuning and using cutting-edge techniques such as Retrieval-Augmented Generation (RAG) and intelligent agents. This project is ideal if you know some Python and deep learning, and it offers both theory and hands-on code to help you master LLM development and apply it in real-world AI tasks. This can boost your skills and confidence in AI model building and research.
https://github.com/datawhalechina/happy-llm
https://code.tutsplus.com/tutorials/behavior-driven-development-in-python--net-26547
Behavior-Driven Development (which we will now refer to as "#BDD") follows on from the ideas and principles introduced in #Test-Driven Development. The key points of writing tests before code really apply to BDD as well. The idea is to not only test your code at the granular level with unit tests, but also test your application end to end, using acceptance tests. We will introduce this style of testing with the use of the Lettuce testing framework.
http://pythonhosted.org/behave/
behave is behaviour-driven development, Python style.
Behavior-driven development (or #BDD) is an agile software development technique that encourages collaboration between developers, #QA and non-technical or business participants in a software project. We have a page further describing this philosophy.
behave uses tests written in a natural language style, backed up by Python code.
Once you’ve installed behave, we recommend reading the
tutorial first and then
feature test setup,
behave API and
related software (things that you can combine with behave)
finally: how to use and configure the behave tool.
https://pypi.python.org/pypi/pytest-bdd
#BDD library for the py.test runner
#pytest-bdd implements a subset of Gherkin language for the automation of the project requirements testing and easier behavioral driven development.
Unlike many other BDD tools it doesn’t require a separate runner and benefits from the power and flexibility of the #pytest. It allows to unify your unit and functional #tests, easier continuous integration server configuration and maximal reuse of the tests setup.
Pytest fixtures written for the #unit_test s can be reused for the setup and actions mentioned in the feature steps with dependency injection, which allows a true BDD just-enough specification of the requirements without maintaining any context object containing the side effects of the Gherkin. imperative declarations.