Hands-on Course Using OpenAI Models and the Hugging Face Library
A hands-on course using models from OpenAI and the Hugging Face library, divided into three major sections.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- License
- MIT
- Languages
- Jupyter Notebook
- Maintainer
- peremartra
- Verified
What it is
This is the unofficial repository for the book Large Language Models: Apply and Implement Strategies for Large Language Models, published by Apress. The book is based on the content of this repository, but the notebooks are being updated, and new examples and chapters are being incorporated. The course provides a hands-on experience using models from OpenAI and the Hugging Face library. The course is divided into three major sections.
Main features
The course works on an example of Retrieval Augmented Generation using information from various news datasets stored in ChromaDB.
LangChain allows chaining calls to models and other systems, so that applications based on large language models can be built.
Giskard is a solution that allows evaluating a complete RAG solution.
Knowledge Distillation involves training a smaller "student" model to mimic a larger, well-trained "teacher" model.
Getting started
Each lesson consists of notebooks and articles.
The notebooks contain sufficient information for understanding the code within them, and the article provides more detailed explanations about the code and the topic covered.
Most of the notebooks are hosted on Colab, while a few are on Kaggle.
Kaggle provides more memory in the free version compared to Colab, but the author finds that copying and sharing notebooks is simpler in Colab, and not everyone has a Kaggle account.
The notebooks can be run in your own environment, or you can opt for the Pro version of Colab.
Who it is for
The course on GitHub does not contain all the information that is in the book. Each project may have more than one possible implementation, as often there is not just one perfect solution. The projects section also delves into LLMOps-related topics, although they are not the primary focus of the course.
Some of the notebooks require more memory than what the free version of Colab provides. Prompt tuning is an additive technique, and the weights of the pre-trained model are not modified. Large Language Models are not a standalone solution.
The RAG system is enhanced with a semantic cache layer capable of determining if a similar question has been asked before. The course creates a comment response system using a two-model pipeline built with LangChain. The course explores the ROUGE metric to measure the quality of summaries generated by a language model.
In the first pruning notebook, the pruning process is applied to the feedforward layers of a distilGPT2 model.
Related tools
Related tools listed on this site.
阿里云百炼
Alibaba Cloud Bailian is a model-service and application-development platform for model inference, knowledge bases, agents and workflows.
FastGPT
Agent platform for enterprise AI applications and knowledge bases, combining visual workflows, model connections and RAG retrieval.
Dataify
AI data-services platform. Its official site describes datasets for training, evaluation and RAG, webpage/search/video data APIs and network resources, primarily supplying data for models and applications.
OpenBMB
OpenBMB’s open-model community entry. Its public page organizes MiniCPM, AgentCPM, VoxCPM, UltraRAG and other models/projects, with community updates.
文心大模型
ERNIE (Wenxin large model) is Baidu's large-model family; its official ERNIE Blog publishes ERNIE 5.x and other models, the ERNIE-Image text-to-image model and related papers, and links to ERNIE Bot, the Qianfan platform and AI Studio.
Open LLM Leaderboard
Hugging Face Space published by the open-llm-leaderboard organization, described as an interactive leaderboard of open-source language models across tests such as IFEval, BBH, MATH, GPQA, MUSR and MMLU-PRO.
Genmo
The site says Genmo is developing open video world models; Mochi 1 is its open-source text-to-video model, usable online in the Playground or run locally via the open-source repository or ComfyUI.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/peremartra/Large-Language-Model-Notebooks-CourseFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.