Gguf Sharded LaMini Flan T5 248M

🚀 Felladrin/LaMini-Flan-T5-248M-Q5_K_S-GGUF

This model is converted to GGUF format from MBZUAI/LaMini-Flan-T5-248M, offering text - to - text generation capabilities.

🚀 Quick Start

This model was converted to GGUF format from MBZUAI/LaMini-Flan-T5-248M using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

✨ Features

• Text - to - text Generation: Capable of generating text based on input instructions.
• Converted to GGUF: Converted from the original model to the GGUF format for better compatibility.

📦 Installation

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

brew install llama.cpp

💻 Usage Examples

Basic Usage

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Felladrin/LaMini-Flan-T5-248M-Q5_K_S-GGUF --hf-file lamini-flan-t5-248m-q5_k_s-imat.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Felladrin/LaMini-Flan-T5-248M-Q5_K_S-GGUF --hf-file lamini-flan-t5-248m-q5_k_s-imat.gguf -c 2048

Advanced Usage

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

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.

./llama-cli --hf-repo Felladrin/LaMini-Flan-T5-248M-Q5_K_S-GGUF --hf-file lamini-flan-t5-248m-q5_k_s-imat.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Felladrin/LaMini-Flan-T5-248M-Q5_K_S-GGUF --hf-file lamini-flan-t5-248m-q5_k_s-imat.gguf -c 2048

📄 License

This model is released under the cc-by-nc-4.0 license.