GGUF
Russian
llama-cpp
gguf-my-repo
DavidAU's picture
Upload README.md with huggingface_hub
0bc3a3d verified
metadata
language:
  - ru
license: other
tags:
  - llama-cpp
  - gguf-my-repo
datasets:
  - IlyaGusev/ru_turbo_saiga
  - IlyaGusev/ru_sharegpt_cleaned
  - IlyaGusev/oasst1_ru_main_branch
  - IlyaGusev/gpt_roleplay_realm
  - lksy/ru_instruct_gpt4
license_name: llama3
license_link: https://llama.meta.com/llama3/license/

DavidAU/saiga_llama3_8b-Q8_0-GGUF

This model was converted to GGUF format from IlyaGusev/saiga_llama3_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 DavidAU/saiga_llama3_8b-Q8_0-GGUF --model saiga_llama3_8b.Q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo DavidAU/saiga_llama3_8b-Q8_0-GGUF --model saiga_llama3_8b.Q8_0.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 saiga_llama3_8b.Q8_0.gguf -n 128