Update README.md

README.md

@@ -128,37 +128,37 @@ model-index:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix Python
+      name: HumanEvalFixTests Python
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: 23.6
+      value: 18.38
       verified: false
   - task:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix JavaScript
+      name: HumanEvalFixTests JavaScript
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 12.28
       verified: false
   - task:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix Java
+      name: HumanEvalFixTests Java
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 15.12
       verified: false
   - task:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix Go
+      name: HumanEvalFixTests Go
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
@@ -168,27 +168,27 @@ model-index:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix C++
+      name: HumanEvalFixTests C++
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 13.17
       verified: false
   - task:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix Rust
+      name: HumanEvalFixTests Rust
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 2.8
       verified: false
   - task:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalFix Average
+      name: HumanEvalFixTests Average
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
@@ -204,7 +204,37 @@ model-index:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalExplain Python
+      name: HumanEvalFixDocs Python
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 26.92
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalFixDocs JavaScript
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 26.85
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalFixDocs Java
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 30.76
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalFixDocs Go
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
@@ -214,12 +244,56 @@ model-index:
       type: text-generation
     dataset:
       type: bigcode/humanevalpack
-      name: HumanEvalExplain JavaScript
+      name: HumanEvalFixDocs C++
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 25.94
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalFixDocs Rust
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 8.44
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalFixDocs Average
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
       value: -1
       verified: false
+
+
+
+     
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalExplain Python
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 26.46
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: bigcode/humanevalpack
+      name: HumanEvalExplain JavaScript
+    metrics:
+    - name: pass@1 (T=0.2)
+      type: pass@1
+      value: 17.86
+      verified: false
   - task:
       type: text-generation
     dataset:
@@ -228,7 +302,7 @@ model-index:
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 20.94
       verified: false
   - task:
       type: text-generation
@@ -248,7 +322,7 @@ model-index:
     metrics:
     - name: pass@1 (T=0.2)
       type: pass@1
-      value: -1
+      value: 18.78
       verified: false
   - task:
       type: text-generation