hus960's picture
Upload README.md with huggingface_hub
a666c2b verified
metadata
language:
  - en
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - llama-cpp
  - gguf-my-repo
base_model: unsloth/llama-3-8b-bnb-4bit
datasets:
  - tatsu-lab/alpaca
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/njn9I-gHjyq0lMyjF0lZF.jpeg

hus960/Llama-3-NeuralPaca-8b-Q4_K_M-GGUF

This model was converted to GGUF format from NeuralNovel/Llama-3-NeuralPaca-8b 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 hus960/Llama-3-NeuralPaca-8b-Q4_K_M-GGUF --model llama-3-neuralpaca-8b.Q4_K_M.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo hus960/Llama-3-NeuralPaca-8b-Q4_K_M-GGUF --model llama-3-neuralpaca-8b.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 llama-3-neuralpaca-8b.Q4_K_M.gguf -n 128