Update inference config (v0.1.0 label)

INFERENCE_CONFIG.md

@@ -1,10 +1,10 @@
-# Inference Endpoint Configuration (v0.1.1)
+# Inference Endpoint Configuration (v0.1.0)
 
 ## Model Details
-- **Model**: MORBID-Actuarial v0.1.1 Conversational
+- **Model**: MORBID-Actuarial v0.1.0 Conversational
 - **Type**: Causal Language Model (Conversational)
 - **Base**: TinyLlama-1.1B
-- **Handler**: Custom handler.py (v0.1.1) included
+- **Handler**: Custom handler.py included
 
 ## Recommended Configuration
 - **Instance Type**: GPU Small (1x NVIDIA T4)
@@ -27,12 +27,15 @@ def query(payload):
     response = requests.post(API_URL, headers=headers, json=payload)
     return response.json()
 
-# Test queries
+# Test queries (tighter generation under the hood)
 output = query({
-    "inputs": "Hi, how are you?",
+    "inputs": "Human: Help me price a level annuity immediate paying 1000/year at 5%
+Assistant:",
     "parameters": {
-        "max_new_tokens": 100,
-        "temperature": 0.8
+        "max_new_tokens": 220,
+        "temperature": 0.35,
+        "top_p": 0.9,
+        "repetition_penalty": 1.15
     }
 })
 ```
@@ -41,4 +44,4 @@ output = query({
 - Conversational AI with personality
 - Actuarial expertise (97.8% accuracy on exams)
 - Multi-turn context retention and reduced artifacts
-- Tighter generation with stop handling and bad-words filtering
+- Tighter generation and stop handling