Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/yoshoku/llama_cpp.rb
llama_cpp provides Ruby bindings for llama.cpp
https://github.com/yoshoku/llama_cpp.rb
ai gem llama llm ruby
Last synced: 8 days ago
JSON representation
llama_cpp provides Ruby bindings for llama.cpp
- Host: GitHub
- URL: https://github.com/yoshoku/llama_cpp.rb
- Owner: yoshoku
- License: mit
- Created: 2023-03-31T12:49:20.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-16T11:52:16.000Z (about 2 months ago)
- Last Synced: 2024-10-29T10:05:01.281Z (9 days ago)
- Topics: ai, gem, llama, llm, ruby
- Language: C++
- Homepage: https://rubygems.org/gems/llama_cpp
- Size: 6.44 MB
- Stars: 196
- Watchers: 12
- Forks: 15
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE.txt
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# llama_cpp.rb
[](https://badge.fury.io/rb/llama_cpp)
[](https://github.com/yoshoku/llama_cpp.rb/blob/main/LICENSE.txt)
[](https://yoshoku.github.io/llama_cpp.rb/doc/)
llama_cpp.rb provides Ruby bindings for the [llama.cpp](https://github.com/ggerganov/llama.cpp).
This gem is still under development and may undergo many changes in the future.
## Installation
Install the llama.cpp. If you use homebrew, install it by executing:
```sh
$ brew install llama.cpp
```
Install the gem and add to the application's Gemfile by executing:
```sh
$ bundle config --local build.llama_cpp "--with-opt-dir=/opt/homebrew/"
$ bundle add llama_cpp
```
If bundler is not being used to manage dependencies, install the gem by executing:
```sh
$ gem install llama_cpp -- --with-opt-dir=/opt/homebrew
```
## Usage
Prepare the quantized model by refering to [the usage section on the llama.cpp README](https://github.com/ggerganov/llama.cpp#usage).
For example, you could prepare the quatization model based on
[open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)
or more useful in the context of Ruby might be a smaller model such as
[tiny_llama_1b](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0):
```sh
$ cd ~/
$ brew install git-lfs
$ git lfs install
$ git clone https://github.com/ggerganov/llama.cpp.git
$ cd llama.cpp
$ python3 -m pip install -r requirements.txt
$ cd models
$ git clone https://huggingface.co/openlm-research/open_llama_7b
$ cd ../
$ python3 convert-hf-to-gguf.py models/open_llama_7b
$ make
$ ./llama-quantize ./models/open_llama_7b/ggml-model-f16.gguf ./models/open_llama_7b/ggml-model-q4_0.bin q4_0
```
An example of Ruby code that generates sentences with the quantization model is as follows:
```ruby
require 'llama_cpp'
model_params = LLaMACpp::ModelParams.new
model = LLaMACpp::Model.new(model_path: '/home/user/llama.cpp/models/open_llama_7b/ggml-model-q4_0.bin', params: model_params)
context_params = LLaMACpp::ContextParams.new
context_params.seed = 42
context = LLaMACpp::Context.new(model: model, params: context_params)
puts LLaMACpp.generate(context, 'Hello, World.')
```
## Examples
There is a sample program in the [examples](https://github.com/yoshoku/llama_cpp.rb/tree/main/examples) directory that allow interactvie communication like ChatGPT.
```sh
$ git clone https://github.com/yoshoku/llama_cpp.rb.git
$ cd examples
$ bundle install
$ ruby chat.rb --model /home/user/llama.cpp/models/open_llama_7b/ggml-model-q4_0.bin --seed 2023
...
User: Who is the originator of the Ruby programming language?
Bob: The originator of the Ruby programming language is Mr. Yukihiro Matsumoto.
User:
```
Japanse chat is also possible using the [Vicuna model on Hugging Face](https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized).
```sh
$ wget https://huggingface.co/CRD716/ggml-vicuna-1.1-quantized/resolve/main/ggml-vicuna-7b-1.1-q4_0.bin
$ ruby chat.rb --model ggml-vicuna-7b-1.1-q4_0.bin --file prompt_jp.txt
```
## Contributing
Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/llama_cpp.rb.
This project is intended to be a safe, welcoming space for collaboration,
and contributors are expected to adhere to the [code of conduct](https://github.com/yohsoku/llama_cpp.rb/blob/main/CODE_OF_CONDUCT.md).
## License
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
## Code of Conduct
Everyone interacting in the LlamaCpp project's codebases, issue trackers,
chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/llama_cpp.rb/blob/main/CODE_OF_CONDUCT.md).