Llama Shepherd is a command-line tool for quickly managing and experimenting with multiple versions of llama inference implementations. Originating from llama2.c project by Andrej Karpathy.
To list available llama options, use the following command:
python3 llamashepherd/main.py list [Optional][LANGUAGE]
Replace [LANGUAGE] with the desired language to filter options. If not specified, all options will be displayed.
To interactively install llama options, use the following command:
python3 llamashepherd/main.py install
To initialize llama models, use the following command:
python3 llamashepherd/main.py models
This command allows you to download and configure the Tokenizer and/or TinyLLama models.
This project is licensed under the MIT License - see the LICENSE file for details.