Update README.md

README.md

@@ -21,26 +21,6 @@ tags:
 model-index:
 - name: granite-3b-code-base-128k
   results:
-  - task:
-      type: text-generation
-    dataset:
-        type: mbpp
-        name: MBPP
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 36.0
-      veriefied: false     
-  - task:
-      type: text-generation
-    dataset:
-        type: evalplus/mbppplus 
-        name: MBPP+
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 45.1
-      veriefied: false
   - task:
       type: text-generation
     dataset:
@@ -49,178 +29,48 @@ model-index:
     metrics:
     - name: pass@1
       type: pass@1
-      value: 36.6
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name: HumanEvalSynthesis(JavaScript)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 37.2
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name: HumanEvalSynthesis(Java)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 40.9
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name: HumanEvalSynthesis(Go)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 26.2
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name: HumanEvalSynthesis(C++)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 35.4
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name: HumanEvalSynthesis(Rust)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 22.0
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(Python)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 25.0
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(JavaScript)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 18.9
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(Java)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 29.9
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(Go)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 17.1
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(C++)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 26.8
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalExplain(Rust)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 14.0
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalFix(Python)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 18.3
-      veriefied: false
-  - task:
-      type: text-generation
-    dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalFix(JavaScript)
-    metrics:
-    - name: pass@1
-      type: pass@1
-      value: 23.2
-      veriefied: false
+      value: 36.0
+      verified: false
   - task:
       type: text-generation
     dataset:
         type: bigcode/humanevalpack  
-        name:  HumanEvalFix(Java)
+        name: HumanEvalSynthesis(Average)
     metrics:
     - name: pass@1
       type: pass@1
-      value: 29.9
-      veriefied: false
+      value: 30.5
+      verified: false
   - task:
       type: text-generation
     dataset:
         type: bigcode/humanevalpack  
-        name:  HumanEvalFix(Go)
+        name:  HumanEvalExplain(Average)
     metrics:
     - name: pass@1
       type: pass@1
-      value: 24.4
-      veriefied: false
+      value: 22.4
+      verified: false
   - task:
       type: text-generation
     dataset:
         type: bigcode/humanevalpack  
-        name:  HumanEvalFix(C++)
+        name:  HumanEvalFix(Average)
     metrics:
     - name: pass@1
       type: pass@1
-      value: 16.5 
-      veriefied: false
+      value: 19.9
+      verified: false
   - task:
       type: text-generation
     dataset:
-        type: bigcode/humanevalpack  
-        name:  HumanEvalFix(Rust)
+        type: repoqa  
+        name:  RepoQA
     metrics:
     - name: pass@1
       type: pass@1
       value: 3.7
-      veriefied: false
+      verified: false
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)