Automate Dataset Creation for Llama-2 with GPT-4!

In this video, we will look at the get-llm-trainer project that automates the dataset creation and fine-tuning process for Llama-2 models. It utilizes the power of GPT-4 to create a dataset for a given task and then fine-tune a llama2 model using the dataset.
#llama2 #finetune #largelanguagemodels #gpt4
▬▬▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Support my work on Patreon: Patreon.com/PromptEngineering
🦾 Discord: / discord
▶️️ Subscribe: www.youtube.com/@engineerprom...
📧 Business Contact: [e-mail]
💼Consulting: calendly.com/engineerprompt/c...
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
LINKS:
Github repo: github.com/mshumer/gpt-llm-tr...
Google Colab: colab.research.google.com/dri...
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
All Interesting Videos:
Everything LangChain: • LangChain
Everything LLM: • Large Language Models
Everything Midjourney: • MidJourney Tutorials
AI Image Generation: • AI Image Generation Tu...

[@engineerprompt]

Want to connect? 💼Consulting: calendly.com/engineerprompt/consulting-call 🦾 Discord: discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: ko-fi.com/promptengineering |🔴 Join Patreon: Patreon.com/PromptEngineering

[@sahulsumra7025]

It's really good content

[@engineerprompt]

Thank you!

[@kalhosni]

Thanks a lot. However, I got "NameError: name 'load_dataset' is not defined: at the top of "Load Datasets and Train" section. The path is correct and your copy seemed to work just fine???

[@WeylandLabs]

Very Nice !

[@engineerprompt]

Thank you very much!

[@alx8439]

What was the purpose of trying to use NousResearch model instead of the original Llama model by Meta?

[@UncleDao]

The two models are similar, except that if using Llama model, you need to login hugging face to download, if using NousResearch model, there is no need.

[@andyjm2k]

I was under the impression that the openai terms of service prevents you from using GPT4 to train another model.

[@Timotheeee1]

only if your new model competes with them

[@ludwigvanbeethoven61]

nice, is it also possible to run a LLM on Visual Studio Code instead of Jupiter?

[@engineerprompt]

Yes, the process will be similar

[@lrkx_]

Would you be able to fine-tune a 7B parameter model locally on a MacBook Pro M2 with enough RAM? Really curious to see if it’s possible…

[@engineerprompt]

I haven’t had luck with it, so probably not

[@satyamgupta2182]

@@engineerprompt did you come across a solution?

[@alx8439]

Also without the comparison to the original non-fined-tuned Llama, the effectiveness of this fine tuning says nothing. It's like adding a new mechanical part to your car and measure max speed without making the same measurement before the installation

[@alejandrofernandez3478]

I wonder if soon an llm could be taught to train itself on whatever it wanted or was told to learn

[@texasfossilguy]

youd have to have a lot of money or a very powerful architecture

[@texasfossilguy]

it also is important to note, it doesn't want, feel, or need anything unless you somehow program that into it.

[@user-jq1gc8lt7s]

thank you for all this great job , and where I can find discord group

[@engineerprompt]

In the description of the video :)

[@RidvanGER]

Is it possible to use any kind of source code(python, c++ or c#) as a dataset to train llama 2 or any other LLM? Thank you!

[@engineerprompt]

Yes, but you will need a relatively large dataset for it to train properly.

[@tareksahalia]

السنة من أعطى قيمة لهذه الطائفة

[@azzorkimaroc4879]

first comment

[@mastamindchaan387]

Nothing to do with a "Dataset". This is "how to train ChatGPT to respond to a specific prompt"

[@troywoodson7355]

NousResearch/llama-2-7b-chat-hf is no longer available. What model would you recommend instead?

[@engineerprompt]

If you have the access token then use the meta original version