Training the Granite Model with InstructLab with Open WebUI!

Learn how to train the #ibm #granite model with #instructlab and then deploy and run the #openwebui! Paul and JJ built it up from the ground up on a #mac m3, and show you how easy it is. Code -- mkdir instructlab cd instructlab python3 -m venv --upgrade-deps venv source venv/bin/activate pip install instructlab pip cache remove llama_cpp_python pip install --force-reinstall llama_cpp_python==0.2.75 -C cmake.args="-DLLAMA_METAL=on" pip install instructlab` ilab config init ilab download --repository instructlab/granite-7b-lab-GGUF --filename=granite-7b-lab-Q4_K_M.gguf ilab serve --model-path models/granite-7b-lab-Q4_K_M.gguf` wget https://gist.githubusercontent.com/jjasghar/485b30c5fd1c301bc6ea0ddbf2957c12/raw/cf5695ce0172c023c0b16b603e350f9e1240ee57/qna.yaml ilab model download ilab serve --model-path models/merlinite-7b-lab-Q4_K_M.gguf ilab data generate ilab model train --model-dir instructlab/granite-7b-lab --tokenizer-dir models/granite-7b-lab --model-name instructlab/granite-7b-lab ilab model test --model-dir instructlab-granite-7b-lab-mlx-q ilab model convert --model-dir instructlab-granite-7b-lab-mlx-q ilab model serve --model-path instructlab-granite-7b-lab-trained/instructlab-granite-7b-lab-Q4_K_M.gguf