The GPT4-x-Alpaca is a remarkable open-source AI LLM model that operates without censorship, surpassing GPT-4 in performance. In this video, I will demonstrate the capabilities of this extraordinary LLM model. I will guide you through the process of installing GPT4-x-Alpaca on your computer using the llama.cpp package.
Vicuna is an open-source AI project that purportedly provides 90% of the power of ChatGPT. I will also demonstrate how to install Vicuna on your PC using the llama.cpp package for CPU.
Links:
Llama.cpp: https://github.com/ggerganov/llama.cpp (https://github.com/ggerganov/llama.cpp)
Vicuna: https://vicuna.lmsys.org/ (https://vicuna.lmsys.org/)
Vicuna Weights: https://huggingface.co/anon8231489123... (https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g)
GPT4 x Alpaca Model Weights: https://huggingface.co/anon8231489123... (https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g/tree/main)
GPT4 x Alpaca Dataset: https://github.com/teknium1/GPTeacher (https://github.com/teknium1/GPTeacher)
Contents of run.bat file (copy below the line):
I have increased the number of threads to 32 this will speed up the answering a lot.
title llama.cpp
:start
main -i --interactive-first -r "### Human:" --memory_f32 --mlock --top_k 120 --top_p 0-9 --keep -1 --threads 30 --color --temp 0 -c 2048 -n -1 --repeat_penalty 1.2 --instruct -m ggml-model-q4_1.bin
echo -- DONE --
pause
goto start