update to modern bert

README.md

@@ -7,34 +7,33 @@ tags:
 - nli
 - cross-encoder
 - intent-routing
-- debberta
+- modernbert
 pipeline_tag: zero-shot-classification
 widget:
 - text: Generate a formal project proposal in Word format.
-  candidate_labels: a Word document creation request, an Excel spreadsheet creation
-    request, a PowerPoint presentation deck creation request, a PDF document analysis
-    query, general chitchat
+  candidate_labels: a Word document creation request, an Excel spreadsheet creation request, a PowerPoint presentation deck creation request, a PDF document analysis query, general chitchat
 ---
 
-# MarkOne 
+# MarkOne
 
-**MarkOne** is a high-precision, zero-shot NLI cross-encoder model designed for **dynamic intent routing and query classification** within modular AI architectures .
+**MarkOne** is a high-precision, zero-shot NLI cross-encoder model powered by **ModernBERT** designed for dynamic intent routing and query classification within modular AI architectures.
 
-It evaluates user prompts against arbitrary numbers of candidate choice labels (N = 3, 6, 8,..) by computing sequence pair entailment probabilities without requiring dedicated single-label classification fine-tuning for every domain.
+It evaluates user prompts against arbitrary numbers of candidate choice labels (N = 3, 6, 8,..) by computing sequence pair entailment probabilities using modern attention mechanics and an expanded context window.
 
 ---
 
-## 🌟 Key Features
+## Key Features
 
+- **ModernBERT Backbone:** Built on ModernBERT architecture featuring FlashAttention, unpadded processing, and Rotary Positional Embeddings (RoPE) for blazing-fast inference.
+- **Extended Context Window:** Natively supports up to 8,192 tokens, allowing for rich, detailed candidate descriptions and long-form document inputs.
 - **Dynamic Choice Counts:** Handles variable numbers of candidate labels on the fly across different routing domains.
 - **Cross-Encoder Accuracy:** Outperforms single-text classifiers by evaluating joint attention over `(Premise, Hypothesis)` pairs.
-- **DocGeniee Native:** Pre-configured for routing document generation workflows (Word, Excel, PowerPoint), PDF RAG queries, and chitchat/out-of-scope filtering.
 
 ---
 
-## 🚀 Quickstart & Usage
+## Quickstart & Usage
 
-Because **MarkOne** operates as an NLI cross-encoder, it evaluates candidate choices by pairing the input prompt as a **Premise** with a set of generated candidate **Hypotheses**.
+MarkOne operates as an NLI cross-encoder, evaluating candidate choices by pairing the input prompt as a Premise with a set of generated candidate Hypotheses.
 
 ### Zero-Shot NLI Classification (Python)
 
@@ -44,16 +43,23 @@ import torch
 import torch.nn.functional as F
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
 
-# Load model and tokenizer
-MODEL_ID = "ChandruK/MarkOne"
+# Load ModernBERT NLI model and tokenizer
+MODEL_ID = "dleemiller/ModernCE-base-nli"
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID).to(device)
 model.eval()
 
-# Entailment label index (Index 2 for standard DeBERTa MNLI architecture)
-ENTAILMENT_IDX = 2
+# Dynamically resolve Entailment label index from config
+label_mapping = model.config.id2label
+ENTAILMENT_IDX = None
+for idx, label_name in label_mapping.items():
+    if label_name.lower() in ["entailment", "entail"]:
+        ENTAILMENT_IDX = idx
+        break
+if ENTAILMENT_IDX is None:
+    ENTAILMENT_IDX = 1
 
 # 1. Define Candidate Labels and Hypothesis Template
 CANDIDATE_LABELS = [
@@ -79,26 +85,23 @@ inputs = tokenizer(
     text_pair=hypotheses,
     padding=True,
     truncation=True,
+    max_length=1024,
     return_tensors="pt",
 ).to(device)
 
 # 5. Model Inference
 with torch.no_grad():
     outputs = model(**inputs)
-    # Extract Entailment logits vector across all dynamic candidates
-    entailment_logits = outputs.logits[:, ENTAILMENT_IDX]
+    logits = outputs.logits
+    entailment_logits = logits[:, ENTAILMENT_IDX] if logits.shape[-1] >= 3 else logits[:, 1]
 
-    # Softmax probability normalization
+    # Softmax probability normalization with temperature scaling
     probabilities = F.softmax(entailment_logits / 0.5, dim=-1)
     top_prob, top_idx = torch.max(probabilities, dim=-1)
 
 predicted_label = CANDIDATE_LABELS[top_idx.item()]
 confidence = top_prob.item() * 100
 
-# =====================================================================
-# MODIFICATION FOR JSON OUTPUT
-# =====================================================================
-
 # Build dictionary containing key details and all category probabilities
 label_scores = {
     label: round(prob.item() * 100, 2)