CRITICAL: Remove all escaped underscores from YAML metadata

README.md

@@ -14,7 +14,7 @@ tags:
 - nlp
 - pragmatics
 datasets:
-- topical_chat
+- topical-chat
 metrics:
 - f1
 - precision
@@ -30,7 +30,7 @@ model-index:
       name: Multi-Label Gricean Maxim Violation Detection
     dataset:
       name: Topical-Chat (GriceBench held-out split, N=1000)
-      type: topical_chat
+      type: topical-chat
       split: test
     metrics:
     - type: f1
@@ -60,9 +60,9 @@ model-index:
 [![HuggingFace](https://img.shields.io/badge/🤗-GriceBench-yellow)](https://huggingface.co/Pushkar27)
 [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
 
-**Part of the GriceBench system** — 
-[GitHub](https://github.com/PushkarPrabhath27/Research-Model) | 
-[🔧 Repair Model](https://huggingface.co/Pushkar27/GriceBench-Repair) | 
+**Part of the GriceBench system** —
+[GitHub](https://github.com/PushkarPrabhath27/Research-Model) |
+[🔧 Repair Model](https://huggingface.co/Pushkar27/GriceBench-Repair) |
 [⚡ DPO Generator](https://huggingface.co/Pushkar27/GriceBench-DPO)
 
 </div>
@@ -92,12 +92,11 @@ import torch.nn as nn
 import json
 from transformers import AutoTokenizer, AutoModel
 
-# ── Define model architecture (must match training) ─────────────────────────
 class MaximDetector(nn.Module):
     def __init__(self, model_name="microsoft/deberta-v3-base", num_maxims=4):
         super().__init__()
         self.encoder = AutoModel.from_pretrained(model_name)
-        hidden = self.encoder.config.hidden_size  # 768
+        hidden = self.encoder.config.hidden_size
         self.classifiers = nn.ModuleList([
             nn.Sequential(
                 nn.Dropout(0.15),
@@ -114,8 +113,6 @@ class MaximDetector(nn.Module):
         cls = outputs.last_hidden_state[:, 0, :]
         return torch.cat([head(cls) for head in self.classifiers], dim=1)
 
-# ── Load model and calibration ──────────────────────────────────────────────
-# Download pytorch_model.pt and temperatures.json from this repo first
 tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-v3-base")
 model = MaximDetector()
 state_dict = torch.load("pytorch_model.pt", map_location="cpu")
@@ -125,9 +122,8 @@ model.eval()
 with open("temperatures.json") as f:
     temperatures = json.load(f)
 
-# ── Detect violations ───────────────────────────────────────────────────────
 def detect_violations(context: str, response: str, evidence: str = "") -> dict:
-    input_text = f"Context: {context}\n\nEvidence: {evidence}\n\nResponse: {response}"
+    input_text = f"Context: {context}\nEvidence: {evidence}\nResponse: {response}"
     inputs = tokenizer(
         input_text, return_tensors="pt",
         max_length=512, truncation=True, padding=True
@@ -142,7 +138,7 @@ def detect_violations(context: str, response: str, evidence: str = "") -> dict:
     ]
 
     with torch.no_grad():
-        logits = model(**inputs)  # Shape: [1, 4]
+        logits = model(**inputs)
 
     probs, violations = {}, {}
     for i, (maxim, temp) in enumerate(zip(maxim_names, temp_values)):
@@ -156,16 +152,12 @@ def detect_violations(context: str, response: str, evidence: str = "") -> dict:
         "is_cooperative": not any(violations.values())
     }
 
-# ── Example ─────────────────────────────────────────────────────────────────
 result = detect_violations(
     context="What do you think about the latest developments in AI?",
-    response="Yes.",   # Too short — Quantity violation
+    response="Yes.",
     evidence="AI has seen rapid advancement in large language models during 2024-2025."
 )
 print(result)
-# {'violations': {'quantity': True, 'quality': False, 'relation': False, 'manner': False},
-#  'probabilities': {'quantity': 0.97, 'quality': 0.02, 'relation': 0.03, 'manner': 0.11},
-#  'is_cooperative': False}
 ```
 
 ---