KULLM3-Q4_K_S-GGUF / README.md
Recaru's picture
Upload README.md with huggingface_hub
6ca64e3 verified
metadata
language:
  - en
  - ko
license: apache-2.0
library_name: transformers
tags:
  - llama-cpp
  - gguf-my-repo
base_model:
  - upstage/SOLAR-10.7B-v1.0

Recaru/KULLM3-Q4_K_S-GGUF

This model was converted to GGUF format from nlpai-lab/KULLM3 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 Recaru/KULLM3-Q4_K_S-GGUF --model kullm3.Q4_K_S.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Recaru/KULLM3-Q4_K_S-GGUF --model kullm3.Q4_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 kullm3.Q4_K_S.gguf -n 128