Drop token_type_ids; DistilBERT doesn't accept them

app.py

@@ -13,18 +13,19 @@ person their proposal will fail. So instead it reports:
 """
 
 import json
+
 import gradio as gr
 import numpy as np
 import torch
 import torch.nn.functional as F
 from datasets import load_dataset
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
 MODEL_ID = "gramajo/nouns-proposal-predictor"
 DATASET_ID = "gramajo/nouns-proposals"
-BREAK_ID = 786          # BreakEven bloc regime change
+BREAK_ID = 786  # BreakEven bloc regime change
 MAX_LENGTH = 512
-AUC = 0.65              # measured, run A (stratified random split)
+AUC = 0.65  # measured, run A (stratified random split)
 ACC, BASELINE = 0.589, 0.502
 
 print("Loading model...")
@@ -54,9 +55,13 @@ def _encode(texts, batch=16):
     for i in range(0, len(texts), batch):
         chunk = texts[i : i + batch]
         enc = tokenizer(
-            chunk, padding=True, truncation=True,
-            max_length=MAX_LENGTH, return_tensors="pt",
+            chunk,
+            padding=True,
+            truncation=True,
+            max_length=MAX_LENGTH,
+            return_tensors="pt",
         )
+        enc.pop("token_type_ids", None)  # DistilBERT has no segment embeddings
         with torch.no_grad():
             out = model(**enc, output_hidden_states=True)
         probs.extend(F.softmax(out.logits, dim=-1)[:, 1].tolist())
@@ -70,7 +75,9 @@ _texts = [(r["title"] + " " + (r.get("description") or ""))[:2000] for r in CORP
 CORPUS_PROBS, CORPUS_EMBS = _encode(_texts)
 _norms = np.linalg.norm(CORPUS_EMBS, axis=1, keepdims=True)
 CORPUS_EMBS_N = CORPUS_EMBS / np.clip(_norms, 1e-9, None)
-POST_PROBS = np.array([CORPUS_PROBS[i] for i, r in enumerate(CORPUS) if int(r["id"]) >= BREAK_ID])
+POST_PROBS = np.array(
+    [CORPUS_PROBS[i] for i, r in enumerate(CORPUS) if int(r["id"]) >= BREAK_ID]
+)
 print("Ready.")
 
 
@@ -125,14 +132,18 @@ def analyze(title, description):
         )
 
     md.append("\n## Most similar past proposals\n")
-    md.append("Read these. They're more informative than any score this tool prints.\n\n")
+    md.append(
+        "Read these. They're more informative than any score this tool prints.\n\n"
+    )
     md.append("| outcome | similarity | proposal |\n|---|---|---|\n")
     for i in top:
         r = CORPUS[i]
         outcome = "✅ passed" if r["passed"] else "❌ failed"
         era = "post-BreakEven" if int(r["id"]) >= BREAK_ID else "pre-BreakEven"
         t = r["title"][:70]
-        md.append(f"| {outcome} | {sims[i]:.2f} | **#{r['id']}** {t} <br/><sub>{era}</sub> |\n")
+        md.append(
+            f"| {outcome} | {sims[i]:.2f} | **#{r['id']}** {t} <br/><sub>{era}</sub> |\n"
+        )
 
     md.append(
         f"\n---\n\n*Model AUC {AUC:.2f} — it ranks proposals better than chance, but it "
@@ -191,9 +202,14 @@ with gr.Blocks(title="Nouns Proposal Check") as demo:
 
     with gr.Row():
         with gr.Column(scale=1):
-            title = gr.Textbox(label="Proposal title", placeholder="Nouns × ...", lines=1)
-            desc = gr.Textbox(label="Proposal description", lines=14,
-                              placeholder="Paste the full proposal body here...")
+            title = gr.Textbox(
+                label="Proposal title", placeholder="Nouns × ...", lines=1
+            )
+            desc = gr.Textbox(
+                label="Proposal description",
+                lines=14,
+                placeholder="Paste the full proposal body here...",
+            )
             btn = gr.Button("Compare against past proposals", variant="primary")
         with gr.Column(scale=1):
             out = gr.Markdown("Enter a proposal to see how it compares.")