mirror of
https://github.com/huggingface/candle.git
synced 2025-06-16 10:38:54 +00:00
33c9b66554
* Add the new gemma models. * Revert the lightning changes. * Support for the 1.1 models.
candle-gemma: 2b and 7b LLMs from Google DeepMind
Gemma is a collection of lightweight open models published by Google Deepmind with a 2b and a 7b variant.
In order to use the example below, you have to accept the license on the HuggingFace Hub Gemma repo and set up your access token via the HuggingFace cli login command.
Running the example
$ cargo run --example gemma --release -- --prompt "fn count_primes(max_n: usize)"
fn count_primes(max_n: usize) -> usize {
let mut primes = vec![true; max_n];
for i in 2..=max_n {
if primes[i] {
for j in i * i..max_n {
primes[j] = false;
}
}
}
primes.len()
}