This model was converted to GGUF format from testboizzz/llama-cendol-fix-merged using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Usage with Chat AI Offline App

Download the app from the Github by downloading its apk file in its Releases, and then install it

Download this model, by clicking on the Files tab

Then, set the model from the app, by selecting this model file

After that you can already start chatting with the AI model

This model is fine tuned on Cendol Collection in which has improved capabilities on conversing in Indonesian Language

Use with llama.cpp

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

bash

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo testboizzz/llama-cendol-fix-merged-Q4_K_M-GGUF --hf-file llama-cendol-fix-merged-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo testboizzz/llama-cendol-fix-merged-Q4_K_M-GGUF --hf-file llama-cendol-fix-merged-q4_k_m.gguf -c 2048

Note: 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 testboizzz/llama-cendol-fix-merged-Q4_K_M-GGUF --hf-file llama-cendol-fix-merged-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo testboizzz/llama-cendol-fix-merged-Q4_K_M-GGUF --hf-file llama-cendol-fix-merged-q4_k_m.gguf -c 2048