Llama.cpp compatible versions of an original
7B model
.
Download one of the versions, for example
model-q4_K.gguf
.
wget https://huggingface.co/IlyaGusev/saiga2_7b_gguf/resolve/main/model-q4_K.gguf
Download
interact_llamacpp.py
wget https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llamacpp.py
How to run:
pip install llama-cpp-python fire
python3 interact_llamacpp.py model-q4_K.gguf
System requirements:
-
10GB RAM for q8_0 and less for smaller quantizations