The course was great! It presented all of the algorithms and complex math in very intuitive and easy to comprehend ways, and I loved that it had a lot of focus on implementation, use cases, and deployment for practical usability. The labs were great, but they were mostly follow along. It'd be nice to have to do a little bit of the coding ourselves as well to truly feel like we're involved.

I was in a rush to finish this course, but it is so well structured and the instructors do such a good job of explaining concepts and technologies that I was able to learn most of the important topics in this rushed timeline. Learning how a model is trained and what considerations go into training one (especially the RLHF) will help me make better informed decisions when evaluating LLMs.

Even though this is a harsh beginning course for non computer science people, it encourages everyone to participate to the world of AI of all types, and explains very well and detailed how to fine tune your skills and specialities to make progress using LLMs. Regardless, if we will or not use AWS service, it opens a good opportunity and window to get good profit out of it.

This course provide very good Gen AI materials and it prompts me to starting to dive deeper into understanding low level knowledges like embedding and tokenizer stuff. I wish they can pick a smaller model that would allow users to use small machine to do pre-training with some optional data and some quiz questions & selections can be rephrased to make them less confusing.

It's a great course and very actionable material.

While I like AWS a lot (they were my first cloud and personal choice), in an academic setting, we should train people in technology in a vendor-agnostic manner (even if AWS is participating in the teaching).

How do these ideas work using other clouds?

I will be coming back for more! Exciting stuff. I can't get enough of it.

Very nice course, good instructors that explain clearly all the technical devcelopments around LLM's. I did many courses developed by deepleaning.ai, but this one is certainly much better, than other courses not given by Andrew Ng. The labs are alo good, but perhaps it would be better that the student has to program a few lines of code. Thet is a little bit too easy now.

The course is a great tour for me toward the generative AI area with comprehensive labs that mention the representative papers, necessary techniques, AI project frameworks, and some tools and libraries. This experience gives me more confidence to explore higher levels in the rapidly developing direction of LLMs, especially after finishing the NLP specialization course.

This is a good course to take after the deep learning specialization series. It builds on top of the Transformer that was introduced in the Sequence Models. The labs take you through the workings of LLM: how to tune it, how to detect bias and how to leverage LLMs with external applications. Thank you to the instructors for very thorough explanations.

Great course. Learned quite a bit state-of-the art techniques for fine tuning LLMs. Ideal for some one with some hands on ML, LLM prompt engineering and python programming language. Labs are great. Nice lecture videos. Instructors are easy to follow and are clear explaining the concepts. Thank you DeepLearning.AI and Amazon team. Great job!

I highly enjoyed the course. The professors are very experienced in this subject and also very didatics. They made it easy to understand some concepts I always needed help with. I found the course very enriching and am already racing to apply the knowledge I have acquired here. Thank you all the team for the effort in creating this course.

Overall Experience: The course provided an excellent overview of working with Large Language Models (LLMs), covering essential concepts like creating LLM models, effective prompting strategies, fine-tuning techniques, and the Generative AI project life cycle. The inclusion of reinforcement learning techniques was also a valuable addition.

Generative AI with LLM another great course from Deeplearning.AI

This course was developed by a very professional team of instructors. I recommend this course for anyone want to understand LLM mechanics and what is required to have a real world application powered by LLM based on the latest research publications and frameworks till today.

Very concentraited and understandable information with links on original papers and resources. Maybe it should be better if course will include more practice. Labs are more like seminars, so you just run code, not writing it at all and still have 100% grade for lab. In my opinion, addition of some practical tasks will improve the course

Exceptional course instructors! It focuses on the practical side of Generative AI models and how to get a LLM running by the end of the course. If you want a more detailed math explanation about how LLMs work you should look elsewhere. However, there are many important insights on the LLM project lifecycle in the practical sense.

An extremely helpful and insightful course. As an AI enthusiast, I found it very useful to get to learn more. Also in the context of job-preparation, this course would really help aspiring Data Scientists or Researches, on helping to gain knowledge on how to create new models and deploy in real-world scenario. Happy Learning !

Gain foundational knowledge, practical skills, and a functional understanding of how generative AI works Dive into the latest research on Gen AI to understand how companies are creating value with cutting-edge technology Instruction from expert AWS AI practitioners who actively build and deploy AI in business use-cases today

This course is absolutely brilliant if you are getting into GenAI & LLMs. It was well explained, covering all topics and very detailed. The labs on AWS is a bonus as you get to work on AWS platform and play with the code and examples provided to you. You can also download these labs offline to experiment later on.

This comprehensive course offers an in-depth exploration of Generative AI with large language models. The instruction is top-notch, and the inclusion of subject matter experts in the discussions adds significant value. I'm a big fan of DeepLearning.AI courses and look forward to completing the rest of the series.

The course covered LLM, Transformer Architecture, Training, Fine-tuning LLM, Optimization techniques etc. The hands on lab also provided opportunity to execute and understand the concept. I humbly feel by adding at least one final lecture on API integration for applications will be useful. Thanks. Devadevan

This is a well-structured course that covers all the important points and gives a complete picture. Even I, who just (06.2023) wrote my master's thesis on "Large Language Models. Learning and Reasoning at the Inference Stage" found interesting new points and references. Thanks to all the course creators!

Gets you jump started to LLM and AI, too much compressed information and you will have lots of q&a so better to do in a group with a lead familiar with prior AI or ML concepts. You might have to do the course twice to thoroughly understand it. Bot so far this the best opening door to all thing LLMs 👌👌👌

This course is beneficial for me regarding Generative AI with Large Language Models. This you so much Coursera, for giving me the opportunity to learn and complete this course free of cost.

Great platform for top-level education. They provide a platform where you can learn whether you have money or not.

An excellent course from a team who is not only adept in what they teach, but is also good at teaching. The structure of the course caters to both - the theoretical and the practical learner. Practical learning through the labs gives a great understanding of LLMs and how they are programmatically managed.

Extremely useful course. Through this course, I got a detailed understanding of open-source LLM models, fine-tuning techniques, and understanding of LLM-enabled product deployment. Moreover, additional resources like research papers and some of the optional videos are very useful for further learning.