ggml versions of OpenLLaMa 13B

For use with llama.cpp.

• Version: 1000B tokens final release
• Project: OpenLLaMA: An Open Reproduction of LLaMA
• Model: openlm-research/open_llama_13b
• llama.cpp 4,5,8-bit quantization: build 567(2d5db48) or later
• llama.cpp newer quantization formats: build 616(99009e7) or later