Update README.md

README.md

@@ -5,7 +5,7 @@ license: apache-2.0
 tags:
 - merge
 - mergekit
-- dare_ties
+- slerp
 - agent
 - gui-automation
 - vision
@@ -181,19 +181,20 @@ This model was merged using **Mergekit**.
 models:
   - model: microsoft/Fara-7B
   - model: ByteDance-Seed/UI-TARS-1.5-7B
-    parameters:
-      density: 0.53
-      weight: 0.5
-merge_method: dare_ties
+merge_method: slerp
 base_model: microsoft/Fara-7B
-parameters:
-  normalize: true
-  int8_mask: true
 dtype: bfloat16
+parameters:
+  t:
+    # 5-point gradient:
+    # 0.1 (Start): Mostly Fara -> Ensures input understanding and English grammar.
+    # 0.3 -> 0.5 (Middle): Blends TARS capability for reasoning and logic.
+    # 0.1 (End): Mostly Fara -> Ensures the output stops correctly and doesn't loop.
+    - value: [0.1, 0.3, 0.5, 0.3, 0.1]
 ```
-*(Note: While `dare_ties` was used, specific inference parameters (temp=0.4, rep_penalty=1.15) are required to stabilize the output, as documented in the Usage section).*
+*(Note: While `slerp` was used, specific inference parameters (temp=0.4, rep_penalty=1.15) are required to stabilize the output, as documented in the Usage section).*
 
-## ⚠️ Limitations
+## Limitations
 
 1.  **Strict Prompting:** The model expects the specific System Prompt defined in the usage class. Without it, it may hallucinate tool names.
 2.  **Repetition:** In extremely long lists (100+ items), the model may repeat. The recommended `repetition_penalty=1.15` fixes this for 99% of cases.