Skip to main content

Reflections on course 'Generative AI with Large Language Models'

 course: Generative AI with Large Language Models

This course is presented by Andrew Ng as the introductory speaker and mainly consists of lectures by AWS engineers who explain various current theories and three practical courses.


Week 1: introduction of LLMs and project lifecycle 

The course introduces the architecture of Large Language Models (LLMs), their conceptual framework, and methods of expansion. It includes practical sessions demonstrating how to load AI and use extension datasets. The lectures cover the initial pre-training phase of AI and discuss the impact of domains on both the overall system and specialized aspects.

Week 2: Fine-Tuning

The course explains how AI, after initial training, can be further expanded to enhance areas required by users. It introduces examples of Fine-Tuning and includes a practical session demonstrating the extension training and integration of AI.

Week 3: Reinforcement learning from human feedback (RLHF) 

The course discusses the social responsibility of AI, including the theory of training AI to remove harmful data, a process that requires human evaluation. It also offers practical lessons as demonstrations. The final part covers the architecture of integrating AI with professional software and the related services provided by AWS.


After completing this course, I found it to be both practical and interesting. Although I didn't pay for the course and therefore couldn't use AWS's environment for the practical lessons.

However, my previous experience using Stable Diffusion allowed me to experiment in Google Colab based on the walkthrough explanations from the practical lessons. Also, drawing from my experience with stabilityai, I created a convenient test Web-App using Flask.


After reviewing the datasets used in the practical lessons, I truly understood the amount of effort the development team put into training AI for conversations. I also feel regret for the early AI models that were misled by a group of internet users. For the average user, extending the training of an existing AI is much more important than creating a new one. Building the necessary functionalities upon an already conversational AI is the approach that can significantly broaden the application scope of AI. Training a basic conversational AI is an arduous process that requires considerable resources and time. If its applications can be expanded, the costs can gradually be distributed, or the income from application-level usage can be reinvested to strengthen and rebuild the foundational conversational AI.

From this course, I unexpectedly learned that conversational AI is not inherently proficient in the computational functions natural to machines. Currently, many enterprise processes are digitized, and for conversational AI to execute calculations or pre-designed business processes, it needs to integrate these functions as external services. From my years of experience in designing game systems and distributed systems, I originally thought this would be straightforward. Creating a universal tool that does everything is challenging, but by loading the necessary functions as required by users, a powerful system can be composed of many small, specialized features. However, it seems that for conversational AI to discern and utilize professional tools, it is not as simple as users operating a process-based system.

From the course, I learned that AI can be enhanced through simple additive methods as well as more resource-intensive rebuilding techniques. Recent studies indicate that AI expanded using the LoRA method can be deconstructed through reverse engineering algorithms. Google is focusing on developing smaller models, AWS is working towards increasing computational efficiency, and OpenAI is aiming to develop more powerful models. AI has lowered the barrier for humans to use technology and has made many ancillary tasks, which previously required significant time and money but weren't the main focus, easily accomplishable. This allows attention to be focused on the primary tasks.


Comments

Post a Comment

Popular posts from this blog

Guide to Preserving HuggingFace Models in Google Colab Environments

Conclusion:  Step 1:  find the model path: ls ~/.cache  Step 2:  Copy the entire folder to Google Drive:  Step 3:  Set model path to the subfolder under snapshot: My Story: I initially began exploring Generative AI (GAI) and Google Colab through Stable Diffusion. In the past, as I mainly wrote server services and console applications, I was less familiar with data science modes like R and Jupyter that can maintain a paused state. I didn't quite understand the heavy burden on Colab of creating a temporary Stable Diffusion WebUI with .ipynb, as suggested by popular guides. I just found it troublesome that connections often took a long time and then dropped, requiring a restart. Recently, while testing new versions of the Stable Diffusion model, and facing challenges due to Colab's policies making various versions of WebUI difficult to run successfully, I started researching how to write my own test programs in Colab. Eventually, I understood that Colab is ess...
Post a Comment
Read more

docker: storage and services

Docker Volume Without going through Docker, accessing files within a Docker image is not easy. Therefore, Docker has a volume feature that allows users to specify the location on the host file system to serve as the access directory for Docker. In other words, a volume is the NFS of a Docker image. Example: Using a volume to store SQLite files. ref:  SQLite for NodeJS: https://www.sqlitetutorial.net/sqlite-nodejs/ Initialize the project. # Setup ExpressJS framework express --view=pug 240324_ejs_sqlite_docker npm init npm install express npm install sqlite3 Test: npm start Initialize docker  Since the directory already contains NodeJS, the Docker Daemon will assist in the setup. Create new docker image docker build -t atfuture7/sqlite01 . Create a folder for Docker, create a container, run it.  mkdir docker_vol docker run -p 3000:3000 -v ./docker_vol:/data --name exp_sqlite atfuture7/sqlite01 After confirming that the container can run co...
3 comments
Read more

Bookmark service (MongoDB & Spring REST)

Completed a working version of Bookmark service. Feeling great~~ ha! ha! Finding something to practice is an efficient way of learning. The project concept is redesigned from a MongoDB project. Weeks ago, I was learning MongoDB and NodeJS. Mixing everything together is my hobby. There might be conflictions, but putting all strengths together has higher potential to resolve difficult and complex problems. Elites getting together might sometimes not be easy, I mean technology, of course. Nice things deserve practice.  Building your first application with MongoDB: Creating a REST API using the MEAN Stack https://www.mongodb.com/blog/post/building-your-first-application-mongodb-creating-rest-api-using-mean-stack-part-1   After redesign…… is ….extremely simple…. But contains enough new topics for me to explore. I’m just a starter of Spring (and a veteran of OO and Cloud programming). Keep everything simple and fast.    I applied to cloud services (like AWS), online artist...
Post a Comment
Read more