llama-3-1 with llama.cpp the best I could ever try.

#3
by wro1952 - opened

Dear llama team,

I could test the recent llama-3-1-8-instruct with llama.cpp.
Up to now the best LLM I could ever try.
Was perfect in analyzing a program structure.
Very efficient in coding - at least C.
Open minded and competent in a discussion based on recent geopolitical events.
And extremely polite and "human".
I used bullerwins Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf with the following prompt:

./llama-cli -t 4 -m ./models/Meta-Llama-3.1-8B-Instruct-Q4_K_S.gguf --log-enable --color -c 8192 --temp 0.7 --mirostat 2 --repeat-penalty 1.1 -n -1 -i --in-prefix "user:" --in-suffix "assistant:" -r "<|eot_id|>" -p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>You are a helpful, respectful and honest assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>Answer in one short sentenc:Who are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>"

I am operating a Linux mint, 32GB RAM, Core I5 pro, 8th Generation, CPU only mode.

So thank you for your great work and the great gift for us all.

Wolf-R. Otto

Sign up or log in to comment