Q6_K quant for https://huggingface.co/abacusai/Liberated-Qwen1.5-72B
llama.cpp commit: e04e04f8fad549bb0b3ec1c91f0413aeb08baf29
Expected sha1sum for the combined file is: 30154585c552c9f6c1adb13821f9e18ea38df3db
Inference API (serverless) does not yet support gguf models for this pipeline type.