Update README.md

README.md

@@ -18,3 +18,28 @@ Recent advances in large language models (LLMs) have highlighted the potential o
 <div align="center">
 <img src="home.jpg" width="80%" />
 </div>
+
+## Inference Parameters
+### 128k setting:
+```
+temperature=0.85
+top_p=0.95
+top_k=20
+max_tokens=131072
+```
+
+### 140k setting (with Yarn)
+```
+temperature=0.85
+top_p=0.95
+top_k=20
+max_tokens=143360
+rope_scaling: {
+    "rope_type": "yarn",
+    "factor": 1.5,
+    "original_max_position_embeddings": 95232
+  }
+```
+### Results
+<img src="overl_results.jpg" width="80%" />
+