metadata
language:
- pl
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
NikolayKozloff/polanka-3b-pretrain-full-v0.4-Q8_0-GGUF
This model was converted to GGUF format from piotr-ai/polanka-3b-pretrain-full-v0.4
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 NikolayKozloff/polanka-3b-pretrain-full-v0.4-Q8_0-GGUF --model polanka-3b-pretrain-full-v0.4.Q8_0.gguf -p "The meaning to life and the universe is"
Server:
llama-server --hf-repo NikolayKozloff/polanka-3b-pretrain-full-v0.4-Q8_0-GGUF --model polanka-3b-pretrain-full-v0.4.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 polanka-3b-pretrain-full-v0.4.Q8_0.gguf -n 128