https://pypi.org/project/fermion-research/ Recent updates to the Python Package Index for fermion-research en https://pypi.org/project/fermion-research/0.1.7/ Five-value sub-2-bit LLMs: chat with a ~2 GB 8B container at native-runtime speed, load it as a Transformers model, or serve it on an OpenAI-compatible endpoint Mon, 27 Jul 2026 21:57:03 GMT https://pypi.org/project/fermion-research/0.1.6/ Five-value sub-2-bit LLMs: chat with a ~2 GB 8B container at native-runtime speed, load it as a Transformers model, or serve it on an OpenAI-compatible endpoint Mon, 27 Jul 2026 18:05:27 GMT https://pypi.org/project/fermion-research/0.1.5/ Five-value sub-2-bit LLMs: chat with a ~2 GB 8B container at native-runtime speed, load it as a Transformers model, or serve it on an OpenAI-compatible endpoint Mon, 27 Jul 2026 15:54:02 GMT