Great video. Glad to see people actually debugging their code. It really helps to better grasp whats going on
Thank you for the tutorial you provided. It's very useful, but please try to speak slower because even AI can't understand what you're saying sometimes. Thank you.
Ayy, this is what I've been looking for
great video, I was stuck on some steps until I found your video.
Thank you so much! This was really helpful!
This is amazing. Really appreciate your efforts, brother.
Really helpful!!! Deserve more views
Its great to try multiple techniques
Epic video, just one question: After saving the model, how can I load it and make inferences.
What if we don't add the <startofstring>< <endofstring>, <pad> and <bot> to the training data? I have a dataset where each sample is formated as [context] [user_question] [bot_answer] and each sample is separated from the next one by an empty line. I am using a pretrained model lighteternal/gpt2-finetuned-greek
Great help - Can you recommend any editor for windows just like yours? and is that possible for you to create a colab or kaggle for same project?
Great video, thanks. I am a beginner studying about these LLM's. I have a small doubt, I have seen people use different data formats to fine-tune different LLMs. For example, the following format can be used for Llama-2: { "instruction": "", "input": "", "output": "" } and sometimes the format below is used for chatglm2-6b: { "content": "", "summary": "" } Is it related to what format was used for pre-training or actually both can be used for different llms, how do I organize my custom data if I want to fine-tune a llm?
great video. just wondering why u used <bot? token between two parts? any reason?
Great Video, thanks
Hi! It was a good video. I would like to know once the model is trained how can we check the accuracy? Can you generate a ROUGE score? That way we know how goo or bad the model is.
Very Informative 😊
Hi there, very good video, really appreciate. Currently we are facing a problem that the input token does not generate any bot output, like <bot:> <endofstring><pad><pad>. Can you help figure it out?
Nothing is generated for me. I used exact code as you used. Can you help understand why this is happening??
i have made my own: <user> Text <End> Ai Text <End is good?
@gingerbread_GB