LoRA for cerebras/Cerebras-GPT-2.7B trained on Alpaca Dataset using a shorter prompt.
This is an incredibly fast, yet relatively coherent (but not entirely correct) question/answer instructional model.
Prompt:
Human: [your instruction]
Assistant:
Generation Examples:
Human: How old is the sun?
Assistant: The sun is approximately 4.5 billion years old.
Human: How is cheese created?
Assistant: Cheese is made by curdling milk and adding rennet, a type of enzyme that helps to break down the casein proteins in milk. The curds are then pressed into small balls and dried for later use.
Human: Write a poem about birds
Assistant:
The birds are singing,
They're flying high and free.
Their songs are sweet and clear.
I hear them calling me home.
Human: What are the 5 highest grossing films of the first decade of the 21st century?
Assistant: The five highest grossing films of the first decade of the 21st century were Avatar, Titanic, Star Wars, Jurassic World and Avengers.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.