Hi Richard just found your channel. Enjoying the information and style of your delivery! Also joined your membership. Will become a CEO someday soon! I had a question for you on this video- I understand how you finetuned the Marv model given 3.5 turbo prompt/completion format , but you also referenced fine tuned models for the visual creator and the power point creator which don’t appear to follow the prompt/completion format. Could you please provide some guidance on that? Are you still using 3.5? Thank you!
Hi @medoeldin! Thank you for your kind words and positive feedback . I’m glad you are enjoying the channel. I’m keen to hear your comments on some of the other topics, as well as suggestions for areas that are interesting to you, but I haven’t yet covered. Welcome to the Lucidate channel, I appreciate your subscription as an MD! This helps fund other top quality content on the channel, and I look forward to welcoming you as one of the select group of CEOs sometime soon. As of the time of writing GPT 3.5 is the most advanced model broadly available for fine tuning from OpenAI. Upon special request, and by providing additional information to OpenAI it is possible to train GPT 4, but this is at OpenAI’s discretion. OpenAI have some great docs and tools to support people looking to Fine Tune, please see: platform.openai.com/docs/guides/fine-tuning. “Marv” is a convention (it is based on the “Marvin the Paranoid Android “ from HHGTTG). Marvin is a sarcastic, self-indulgent somewhat depressed robot in the book and has been used by OpenAI ever since they released GPT3 (and possibly before) to explain to people how they can inject “personality “ into replies via prompts. I’m just continuing that convention and homage to Douglas Adams, but you can use any name in the .jsonl file you want when creating a fine-tune
Thanks Richard for the great and insightful lesson! Just curious how do you get the copra for fine tuning the PowerPoint AI? In what kind of format , can Microsoft copilot be integrated some way in the pipeline to act as the presentation AI agent
A combination of Beautiful Soup to extract the tags from HTML and use of pypdf2.readthedocs.io/en/3.0.0/modules/PdfReader.html to get the text from pff files. So nothing particularly exotic. Then as I said in the video I prompted GPT-4 to produce the format in the JSON file. I didn’t use copilot, but there is no reason at all to expect that you wouldn’t get great results.
Hi Richard just found your channel. Enjoying the information and style of your delivery! Also joined your membership. Will become a CEO someday soon!
I had a question for you on this video- I understand how you finetuned the Marv model given 3.5 turbo prompt/completion format , but you also referenced fine tuned models for the visual creator and the power point creator which don’t appear to follow the prompt/completion format. Could you please provide some guidance on that? Are you still using 3.5? Thank you!
Hi @medoeldin! Thank you for your kind words and positive feedback . I’m glad you are enjoying the channel. I’m keen to hear your comments on some of the other topics, as well as suggestions for areas that are interesting to you, but I haven’t yet covered. Welcome to the Lucidate channel, I appreciate your subscription as an MD! This helps fund other top quality content on the channel, and I look forward to welcoming you as one of the select group of CEOs sometime soon. As of the time of writing GPT 3.5 is the most advanced model broadly available for fine tuning from OpenAI. Upon special request, and by providing additional information to OpenAI it is possible to train GPT 4, but this is at OpenAI’s discretion. OpenAI have some great docs and tools to support people looking to Fine Tune, please see: platform.openai.com/docs/guides/fine-tuning. “Marv” is a convention (it is based on the “Marvin the Paranoid Android “ from HHGTTG). Marvin is a sarcastic, self-indulgent somewhat depressed robot in the book and has been used by OpenAI ever since they released GPT3 (and possibly before) to explain to people how they can inject “personality “ into replies via prompts. I’m just continuing that convention and homage to Douglas Adams, but you can use any name in the .jsonl file you want when creating a fine-tune
Thanks Richard for the great and insightful lesson!
Just curious how do you get the copra for fine tuning the PowerPoint AI? In what kind of format , can Microsoft copilot be integrated some way in the pipeline to act as the presentation AI agent
A combination of Beautiful Soup to extract the tags from HTML and use of pypdf2.readthedocs.io/en/3.0.0/modules/PdfReader.html to get the text from pff files. So nothing particularly exotic. Then as I said in the video I prompted GPT-4 to produce the format in the JSON file. I didn’t use copilot, but there is no reason at all to expect that you wouldn’t get great results.
Got it thanks Richard!
yw!
Is this project available in private repo?
No.