This is a 4-bit quantized ggml file for use with llama.cpp on CPU
GPT4 x Alpaca
(https://huggingface.co/chavinlo/gpt4-x-alpaca)
As a base model we used: https://huggingface.co/chavinlo/alpaca-13b
Finetuned on GPT4's responses, for 3 epochs.
NO LORA
(https://huggingface.co/chavinlo/gpt4-x-alpaca)
As a base model we used: https://huggingface.co/chavinlo/alpaca-13b
Finetuned on GPT4's responses, for 3 epochs.
NO LORA