#!/bin/bash
# InferenceX — Expert Profiling
# Tracks which of 384 experts activate per layer per token.
# Output: CSV with columns [token, layer, expert_id, weight]
# Use this to identify essential experts for model pruning.

MODEL=${1:-"./model.gguf"}
OUTPUT=${2:-"expert_profile.csv"}

./infer_unified "$MODEL" \
  -p "Think step by step about how to build a sustainable desert settlement." \
  -n 20 \
  -t 0.6 \
  --profile "$OUTPUT"

echo ""
echo "Profile saved to: $OUTPUT"
echo "Analyze with: python3 analyze_router.py $OUTPUT"