card: tested quick start (pinned versions, pinned downloads, correct helper paths)

README.md

@@ -28,10 +28,20 @@ The same frozen 10,000 text questions, the same helper code, the same fixed cali
 ## Run it
 
 ```bash
-uv venv mlx && uv pip install --python mlx/bin/python "mlx-lm==0.31.3" "transformers>=4.57" openai
-# the helper from the main repository, with its model client pointed at this MLX checkpoint (see shim_mlx.py there):
-TOKENIZER=openjev-MLX SHIM_MODEL=openjev-MLX READOUT_T=0.85 READOUT_NOUL_T=1.829074 READOUT_NOUL_BIAS=0 READOUT_TARGETED=1 READOUT_INSTR_STYLE=pyrepr \
-  mlx/bin/python shim_mlx.py --helper shim.py --model openjev-MLX --port 3000
+uv venv mlx --python 3.12
+uv pip install --python mlx/bin/python "mlx==0.32.2" "mlx-lm==0.31.3" \
+  "transformers==5.17.0" "openai==3.16.2" "huggingface-hub==1.32.0"
+
+# Download the text-only weights and the two helper files.
+mlx/bin/hf download openjev/openjev-MLX --revision ddbabafe9fbf296d767a91ad99717752530a3927 --local-dir openjev-MLX
+mlx/bin/hf download openjev/openjev helper/shim.py helper/shim_mlx.py \
+  --revision 1c341f65bfe5d50fdb935c71e9739c9e0938d6c4 --local-dir openjev-api
+
+TOKENIZER=openjev-MLX SHIM_MODEL=openjev-MLX \
+READOUT_T=0.85 READOUT_NOUL_T=1.829074 READOUT_NOUL_BIAS=0 \
+READOUT_TARGETED=1 READOUT_INSTR_STYLE=pyrepr SHIM_STAGGER=1 \
+  mlx/bin/python openjev-api/helper/shim_mlx.py \
+  --helper openjev-api/helper/shim.py --model openjev-MLX --port 3000
 ```
 
 Then call `http://localhost:3000/v1/systemone` exactly as the main card describes. `shim_mlx.py` swaps only the helper's model client for an MLX one; prompts, option layout, readout and calibration are the helper's own code.