Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,46 @@
+---
+language:
+  - en
+license: apache-2.0
+library_name: llama-cpp-python
+base_model: katanemo/Arch-Router-1.5B
+tags:
+  - routing
+  - grpo
+  - reinforcement-learning
+  - gguf
+  - lora
+  - unsloth
+  - trl
+  - qwen2
+  - llama-cpp
+  - contract-aware
+  - cost-optimization
+  - query-classification
+model_type: qwen2
+pipeline_tag: text-classification
+datasets:
+  - custom
+metrics:
+  - accuracy
+model-index:
+  - name: ModelGate-Router
+    results:
+      - task:
+          type: text-classification
+          name: Query Complexity Classification
+        metrics:
+          - type: accuracy
+            value: 83.3
+            name: Overall Accuracy (held-out, GGUF Q8_0)
+          - type: accuracy
+            value: 85.7
+            name: Medium Tier Accuracy
+          - type: latency
+            value: 62
+            name: Avg Latency (ms, CUDA)
+---
+
 # ModelGate-Router
 
 GRPO (Group Relative Policy Optimization) fine-tuned routing model for ModelGate's contract-aware query routing. Based on Arch-Router-1.5B. Classifies incoming queries as **simple**, **medium**, or **complex** to route them to the right model tier.