upd3

README.md

@@ -76,16 +76,16 @@ When used with the provided `Modelfile`, the model outputs **exactly one JSON ob
 
 ### Schema
 
-```json
-{
+
+ {
   "verdict": "true | false | uncertain",
   "reason": "string",
   "confidence": 0.0,
   "evidence": ["string"],
   "assumptions": ["string"],
   "next_actions": ["string"]
-}
-Rules
+ }
+## Rules
 confidence is a heuristic value between 0.0 and 1.0
 
 If information is missing, the verdict must be uncertain
@@ -94,36 +94,34 @@ No text outside JSON is expected when the wrapper is used
 
 Stop behavior is enforced by the Modelfile
 
-How to run with Ollama
+## How to run with Ollama
 Create the model locally:
 
-bash
-Copy code
-ollama create logic-reasoner-v2 -f Modelfile
-Example request:
 
-bash
-Copy code
-curl http://localhost:11434/api/generate -d '{
+ ollama create logic-reasoner-v2 -f Modelfile
+## Example request:
+
+
+ curl http://localhost:11434/api/generate -d '{
   "model": "logic-reasoner-v2",
   "stream": false,
   "prompt": "Input: DCGM exporter reports 0 GPUs across all nodes. Question: Is the system healthy?"
-}'
-Quantization
-Format: GGUF
+ }'
+## Quantization
+ Format: GGUF
 
-Quantization: Q4_K_M
+ Quantization: Q4_K_M
 
-Optimized for low-latency operational inference
+ Optimized for low-latency operational inference
 
-Provenance
+## Provenance
 This model was built and packaged as part of the LLM FUN project on NVIDIA DGX B200 infrastructure using:
 
-Kubernetes (RKE2)
+ Kubernetes (RKE2)
 
-Ollama
+ Ollama
 
-OpenWebUI
+ OpenWebUI
 
 The Modelfile is a core part of the model behavior and must be used to reproduce the intended output guarantees.