llama-rb

Llama-rb

Ruby wrapper for llama.cpp.

This was hacked together in a weekend and versions 0.x.x should be considered unstable.

Installation

Install the gem and add to the application's Gemfile by executing:

$ bundle add llama-rb

If bundler is not being used to manage dependencies, install the gem by executing:

$ gem install llama-rb

Usage

Models

Before using this code, you will need to download and process at least one. See ggerganov/llama.cpp.

Example

require 'llama'

m = Llama::Model.new('models/7B/ggml-model-q4_0.bin')
m.predict('hello world')

API

Llama::Model.new

def self.new(
  model,               # path to model file, e.g. "models/7B/ggml-model-q4_0.bin"
  n_predict: 128       # number of tokens to predict
  seed: Time.now.to_i, # RNG seed
)

Llama::Model#predict

def predict(prompt)

Development

git clone --recurse-submodules https://github.com/zfletch/llama-rb
cd llama-rb
./bin/setup

After checking out the repo, run bin/setup to install dependencies. Then, run rake spec to run the tests. You can also run bin/console for an interactive prompt that will allow you to experiment.

To install this gem onto your local machine, run bundle exec rake install. To release a new version, update the version number in version.rb, and then run bundle exec rake release, which will create a git tag for the version, push git commits and the created tag, and push the .gem file to rubygems.org.

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/zfletch/llama-rb.