Run

  1. Install uv.
  2. Install dependencies and start:
uv sync
uv run chat.py

Type a prompt and the model continues it. /quit or Ctrl+C exits.

GPU support

By default uv sync installs the CPU build of PyTorch. Run one of these before uv sync to use a GPU depending on your config.

NVIDIA (CUDA):

cat >> pyproject.toml << 'EOF'

[[tool.uv.index]]
name = "pytorch-cu128"
url = "https://download.pytorch.org/whl/cu128"
explicit = true

[tool.uv.sources]
torch = [{ index = "pytorch-cu128" }]
EOF

AMD (ROCm, Linux only):

cat >> pyproject.toml << 'EOF'

[[tool.uv.index]]
name = "pytorch-rocm"
url = "https://download.pytorch.org/whl/rocm6.4"
explicit = true

[tool.uv.sources]
torch = [{ index = "pytorch-rocm" }]
EOF
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support