mistral-common>=1.8.3 -r ./requirements-convert_legacy_llama.txt --extra-index-url https://download.pytorch.org/whl/cpu ## Embedding Gemma requires PyTorch 2.6.0 or later torch~=2.6.0; platform_machine != "s390x" # torch s390x packages can only be found from nightly builds --extra-index-url https://download.pytorch.org/whl/nightly torch>=0.0.0.dev0; platform_machine == "s390x"