README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - mistral
  - 7b
  - calme
  - llama-cpp
  - gguf-my-repo
inference: false
model_creator: MaziyarPanahi
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
model-index:
  - name: Calme-7B-Instruct-v0.9
    results: []

bunnycore/Calme-7B-Instruct-v0.9-Q5_K_S-GGUF

This model was converted to GGUF format from MaziyarPanahi/Calme-7B-Instruct-v0.9 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 bunnycore/Calme-7B-Instruct-v0.9-Q5_K_S-GGUF --model calme-7b-instruct-v0.9.Q5_K_S.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo bunnycore/Calme-7B-Instruct-v0.9-Q5_K_S-GGUF --model calme-7b-instruct-v0.9.Q5_K_S.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 calme-7b-instruct-v0.9.Q5_K_S.gguf -n 128