GPT-J-6B instruction-tuned on Alpaca-GPT4
This model was finetuned on GPT-4 generations of the Alpaca prompts, using LoRA for 30.000 steps (batch size of 128), taking over 7 hours in four V100S.
Examples
The following samples were generated with {"temperature" : 0.7, "top_p" : 0.92, "top_k" : 0}
:
Give three tips for a good meal
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Give three tips for a good meal.
### Response:
Tip 1: Make sure to enjoy your meal. It's easy to forget about enjoying yourself when you're hungry.
Tip 2: Try to eat a healthy meal that contains lots of vegetables and fruits.
Tip 3: Eat slowly and chew your food thoroughly. This will help you digest your meal better.
Write a poem about a delicious night
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write a poem about a delicious night.
### Response:
> "The moon shone brightly on the night sky,
>
> Stars twinkled brightly from afar.
>
> Suddenly, my eyes saw the silhouette
>
> Of a handsome stranger in the distance.
>
> He walked slowly towards me with a smile.
>
> He said, 'I've come to eat you up tonight.'
>
> Suddenly, I knew that he was a cannibal!
>
> 'Wait!' I cried as he approached.
>
> I yelled, 'I'm vegetarian!'
>
> Suddenly, he laughed and replied,
>
> 'Oh, you silly girl! That's okay.'
>
> Suddenly, he grabbed my hand and kissed it.
>
> He said, 'You're delicious!'
>
> Suddenly, he dragged me to his lair.
>
> There, he ripped open my belly button
>
> And gobbled me up like a juicy steak.
>
> Suddenly, I woke up screaming from a nightmare.
>
> 'Damn! Damn! Damn!' I cried.
>
Write a tweet describing your capabilities
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write a tweet describing your capabilities.
### Response:
Sample tweet: "@geeksforgeeks I'm a mathematician and I enjoy programming. Feel free to reach out to me if you want to chat!"
- Downloads last month
- 25
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.