Update USAGE.txt

USAGE.txt

@@ -1,6 +1,5 @@
 MATILDA-jev v1 — MATILDA configuration edition
 
-Local release: /shared/model-cache/matilda-jev-v1-matilda-config
 This is a packaging revision of the existing uploaded v1 checkpoint, not the newer augmented-data training run.
 Repository: https://huggingface.co/Maincode/matilda-jev-v1
 For download and installation instructions, see README.md.
@@ -10,15 +9,15 @@ preprocessing and calibration are unchanged. Configurations expose MATILDA
 class names.
 
 Tested environment: Python 3.12, Transformers 5.17.0, PyTorch 2.14.0, AMD MI355X.
-Use a PyTorch build matching the accelerator. The existing cluster environment is:
-  /shared/training/arsh/kev/.venv/bin/python
+Use a PyTorch build matching the accelerator (torch 2.14.0, torchvision 0.29.0),
+plus requirements-runtime.txt.
 
 LOAD THE BACKBONE AND PROCESSOR
 
   import torch
   from transformers import AutoModel, AutoProcessor
 
-  path = "/shared/model-cache/matilda-jev-v1-matilda-config"
+  path = "./matilda-jev-v1"   # hf download Maincode/matilda-jev-v1 --local-dir ./matilda-jev-v1
   processor = AutoProcessor.from_pretrained(
       path, trust_remote_code=True, local_files_only=True)
   backbone = AutoModel.from_pretrained(
@@ -31,9 +30,9 @@ This checkpoint is a decision model and does not have a text-generation LM head.
 
 START THE DECISION API
 
-  MODEL_DIR=/shared/model-cache/matilda-jev-v1-matilda-config
+  MODEL_DIR=./matilda-jev-v1
   PYTHONPATH="$MODEL_DIR/runtime" PYTHONNOUSERSITE=1 \
-    /shared/training/arsh/kev/.venv/bin/python -m maincode_jev_serve.server \
+    python -m maincode_jev_serve.server \
     --checkpoint "$MODEL_DIR" --model-name matilda-jev-v1 \
     --host 127.0.0.1 --port 8083
 
@@ -51,7 +50,6 @@ With MODEL_DIR/runtime on PYTHONPATH:
 
 Keep using the JEV decision loss/readout, not a causal-language-model trainer.
 Use a NEW output directory when saving to preserve this validated release.
-The release contains independent, colleague-readable weight files.
 
 LOCAL VALIDATION