mudler's picture
Upload README.md with huggingface_hub
d4f31d9 verified
metadata
language:
  - it
license: llama3
library_name: transformers
tags:
  - mergekit
  - merge
  - llama-cpp
  - gguf-my-repo
base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct
  - DeepMount00/Llama-3-8b-Ita
  - swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA

mudler/Llama-3-8b-ita-ties2-Q4_K_M-GGUF

This model was converted to GGUF format from anakin87/Llama-3-8b-ita-ties2 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 mudler/Llama-3-8b-ita-ties2-Q4_K_M-GGUF --model llama-3-8b-ita-ties2.Q4_K_M.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo mudler/Llama-3-8b-ita-ties2-Q4_K_M-GGUF --model llama-3-8b-ita-ties2.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-3-8b-ita-ties2.Q4_K_M.gguf -n 128