Llama 2 7b Ukrainian Q8 0 GGUF

🚀 NikolayKozloff/Llama-2-7b-Ukrainian-Q8_0-GGUF

This model is a text-generation solution converted to the GGUF format from the base model tartuNLP/Llama-2-7b-Ukrainian. It offers a practical way to generate text, leveraging the power of the Llama-2 architecture.

✨ Features

• Format Conversion: Converted to GGUF format from tartuNLP/Llama-2-7b-Ukrainian using llama.cpp via ggml.ai's GGUF-my-repo space.
• Multi - platform Compatibility: Can be used on Mac and Linux systems.

📦 Installation

Install llama.cpp through brew (works on Mac and Linux):

brew install llama.cpp

💻 Usage Examples

Basic Usage

CLI

llama --hf-repo NikolayKozloff/Llama-2-7b-Ukrainian-Q8_0-GGUF --hf-file llama-2-7b-ukrainian-q8_0.gguf -p "The meaning to life and the universe is"

Server

llama-server --hf-repo NikolayKozloff/Llama-2-7b-Ukrainian-Q8_0-GGUF --hf-file llama-2-7b-ukrainian-q8_0.gguf -c 2048

Advanced Usage

You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo:

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware - specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./main --hf-repo NikolayKozloff/Llama-2-7b-Ukrainian-Q8_0-GGUF --hf-file llama-2-7b-ukrainian-q8_0.gguf -p "The meaning to life and the universe is"

or

./server --hf-repo NikolayKozloff/Llama-2-7b-Ukrainian-Q8_0-GGUF --hf-file llama-2-7b-ukrainian-q8_0.gguf -c 2048

📚 Documentation

Refer to the original model card for more details on the model.

📄 License

This model uses the llama2 license.