|
| 1 | +#!/usr/bin/env bash |
| 2 | +# Tokenizer-level regression: verifies our BPE output matches HF-known-good |
| 3 | +# token IDs for prompts that previously triggered the R3 BPE stale-entry bug. |
| 4 | +# |
| 5 | +# If this test fails, the heap-based BPE merge loop has likely regressed |
| 6 | +# (e.g., someone removed the `tokens[top.pos] < 0` staleness check at |
| 7 | +# tq_tokenizer.c:1442). See bench/results/2026-04-20_bpe_fix_proof.md. |
| 8 | + |
| 9 | +set -u |
| 10 | +BIN="${BIN:-./build/quant}" |
| 11 | +MODELS_DIR="${MODELS_DIR:-models}" |
| 12 | +PASS=0 |
| 13 | +FAIL=0 |
| 14 | +SKIP=0 |
| 15 | + |
| 16 | +check_tokens() { |
| 17 | + local model="$1" |
| 18 | + local prompt="$2" |
| 19 | + local expected="$3" # space-separated token IDs |
| 20 | + local extra_env="${4:-}" |
| 21 | + if [[ ! -f "$MODELS_DIR/$model" ]]; then |
| 22 | + printf " %-40s [SKIP] not found\n" "$model" |
| 23 | + SKIP=$((SKIP+1)) |
| 24 | + return |
| 25 | + fi |
| 26 | + local got |
| 27 | + got=$(env $extra_env TQ_DEBUG=1 "$BIN" "$MODELS_DIR/$model" -p "$prompt" -n 1 -T 0 2>&1 \ |
| 28 | + | grep 'prompt tokens' | sed -E 's/.*prompt tokens \([0-9]+\): //' \ |
| 29 | + | awk '{$1=$1; print}') # normalize whitespace |
| 30 | + if [[ "$got" == "$expected"* ]]; then |
| 31 | + printf " %-40s [PASS] %-20s → %s\n" "$model" "\"$prompt\"" "$got" |
| 32 | + PASS=$((PASS+1)) |
| 33 | + else |
| 34 | + printf " %-40s [FAIL] \"%s\" expected:%s got:%s\n" "$model" "$prompt" "$expected" "$got" |
| 35 | + FAIL=$((FAIL+1)) |
| 36 | + fi |
| 37 | +} |
| 38 | + |
| 39 | +# Qwen3.5/3.6 share a 248320-token vocab different from Qwen3-0.6B's 151936. |
| 40 | +# We only assert the structural property: "Hello" merges to a SINGLE token |
| 41 | +# (not the pre-R3 broken pair [Hel, ll]=two tokens that decoded to "Helll"). |
| 42 | +check_tokens_single() { |
| 43 | + local model="$1" |
| 44 | + local prompt="$2" |
| 45 | + local extra_env="${3:-}" |
| 46 | + if [[ ! -f "$MODELS_DIR/$model" ]]; then |
| 47 | + printf " %-40s [SKIP] not found\n" "$model" |
| 48 | + SKIP=$((SKIP+1)) |
| 49 | + return |
| 50 | + fi |
| 51 | + local got |
| 52 | + got=$(env $extra_env TQ_DEBUG=1 "$BIN" "$MODELS_DIR/$model" -p "$prompt" -n 1 -T 0 2>&1 \ |
| 53 | + | grep 'prompt tokens' | sed -E 's/.*prompt tokens \(([0-9]+)\).*/\1/') |
| 54 | + if [[ "$got" == "1" ]]; then |
| 55 | + printf " %-40s [PASS] \"%s\" → 1 token (merged)\n" "$model" "$prompt" |
| 56 | + PASS=$((PASS+1)) |
| 57 | + else |
| 58 | + printf " %-40s [FAIL] \"%s\" → %s tokens (expected 1)\n" "$model" "$prompt" "$got" |
| 59 | + FAIL=$((FAIL+1)) |
| 60 | + fi |
| 61 | +} |
| 62 | + |
| 63 | +echo "=== Tokenizer regression (BPE stale-entry guard — Pillar 1 R3) ===" |
| 64 | +echo "Models dir: $MODELS_DIR" |
| 65 | +echo "" |
| 66 | + |
| 67 | +# Qwen3 family — the originally broken path. |
| 68 | +# Expected token IDs verified against HF AutoTokenizer 2026-04-20. |
| 69 | +check_tokens "Qwen3-0.6B-Q4_K_M.gguf" "Hello" "9707" \ |
| 70 | + "TQ_NO_METAL=1 TQ_NO_MLOCK=1" |
| 71 | +check_tokens "Qwen3-0.6B-Q4_K_M.gguf" "The quick brown fox" "785 3974 13876 38835" \ |
| 72 | + "TQ_NO_METAL=1 TQ_NO_MLOCK=1" |
| 73 | +check_tokens_single "Qwen3.5-4B-Q4_K_M.gguf" "Hello" \ |
| 74 | + "TQ_NO_METAL=1 TQ_NO_MLOCK=1" |
| 75 | +check_tokens_single "Qwen3.6-35B-A3B-UD-IQ4_XS.gguf" "Hello" \ |
| 76 | + "TQ_NO_METAL=1 TQ_NO_MLOCK=1" |
| 77 | + |
| 78 | +echo "" |
| 79 | +echo "--- Summary --- PASS=$PASS FAIL=$FAIL SKIP=$SKIP" |
| 80 | +[[ "$FAIL" -eq 0 ]] || exit 1 |
| 81 | +exit 0 |
0 commit comments