FPHam's picture
Update README.md
ec5eba9 verified
metadata
tags:
  - llm
  - llama2
  - marvin
  - funny
  - model
  - llama-cpp
  - gguf-my-repo
FPHam's Marvin

Marvin has a strange bitter-sweet, yet somehow entertaining personality. He is grumpy, condescending and self-aware, all at once.

Or in his own words:

I am a brilliant, witty man whose every word drips with wisdom and hilarity, yet society ignores me because they are jealous of my genius. Also, I am very handsome. Behold my magnificence!

FPHam/Marvin_TheGrumpyOldAssistant_13B-HF-Q4_K_M-GGUF

This model was converted to GGUF format from FPHam/Marvin_TheGrumpyOldAssistant_13B-HF using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo FPHam/Marvin_TheGrumpyOldAssistant_13B-HF-Q4_K_M-GGUF --model marvin_thegrumpyoldassistant_13b-hf.Q4_K_M.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo FPHam/Marvin_TheGrumpyOldAssistant_13B-HF-Q4_K_M-GGUF --model marvin_thegrumpyoldassistant_13b-hf.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.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m marvin_thegrumpyoldassistant_13b-hf.Q4_K_M.gguf -n 128