Update README.md

README.md

@@ -12,18 +12,18 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU
+      type: human-exams
+      name: MMLU
     metrics:
     - name: pass@1
       type: pass@1
-      value: 55.00
+      value: 55
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU-Pro
+      type: human-exams
+      name: MMLU-Pro
     metrics:
     - name: pass@1
       type: pass@1
@@ -32,8 +32,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: AGI-Eval
+      type: human-exams
+      name: AGI-Eval
     metrics:
     - name: pass@1
       type: pass@1
@@ -42,28 +42,28 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: WinoGrande
+      type: commonsense
+      name: WinoGrande
     metrics:
     - name: pass@1
       type: pass@1
-      value: 74.90
+      value: 74.9
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: OBQA 
+      type: commonsense
+      name: OBQA
     metrics:
     - name: pass@1
       type: pass@1
-      value: 43.00
+      value: 43
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: SIQA
+      type: commonsense
+      name: SIQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -72,8 +72,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: PIQA
+      type: commonsense
+      name: PIQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -82,8 +82,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: Hellaswag
+      type: commonsense
+      name: Hellaswag
     metrics:
     - name: pass@1
       type: pass@1
@@ -92,18 +92,18 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: TruthfulQA
+      type: commonsense
+      name: TruthfulQA
     metrics:
     - name: pass@1
       type: pass@1
-      value: 39.90
+      value: 39.9
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: reading-comprehension
-        name: BoolQ
+      type: reading-comprehension
+      name: BoolQ
     metrics:
     - name: pass@1
       type: pass@1
@@ -112,8 +112,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reading-comprehension
-        name: SQuAD 2.0
+      type: reading-comprehension
+      name: SQuAD 2.0
     metrics:
     - name: pass@1
       type: pass@1
@@ -122,8 +122,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: ARC-C
+      type: reasoning
+      name: ARC-C
     metrics:
     - name: pass@1
       type: pass@1
@@ -132,8 +132,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: GPQA
+      type: reasoning
+      name: GPQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -142,8 +142,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: BBH
+      type: reasoning
+      name: BBH
     metrics:
     - name: pass@1
       type: pass@1
@@ -152,8 +152,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: MUSR
+      type: reasoning
+      name: MUSR
     metrics:
     - name: pass@1
       type: pass@1
@@ -162,8 +162,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: HumanEval
+      type: code
+      name: HumanEval
     metrics:
     - name: pass@1
       type: pass@1
@@ -172,33 +172,34 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: MBPP
+      type: code
+      name: MBPP
     metrics:
     - name: pass@1
       type: pass@1
-      value: 35.40
-      veriefied: false     
+      value: 35.4
+      veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: math
-        name: GSM8K
+      type: math
+      name: GSM8K
     metrics:
     - name: pass@1
       type: pass@1
       value: 47.23
-      veriefied: false 
+      veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: math
-        name: MATH
+      type: math
+      name: MATH
     metrics:
     - name: pass@1
       type: pass@1
       value: 19.46
       veriefied: false
+new_version: ibm-granite/granite-3.1-2b-base
 ---
 
 <!-- ![image/png](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/figures/granite-3_0-language-models-3x-v1.png) -->
@@ -293,9 +294,7 @@ The use of Large Language Models involves risks and ethical considerations peopl
 - 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
 - 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
 
-We are continuously improving our models, this version is now out of date.  Please check out the latest version of Granite at https://huggingface.co/ibm-granite.
-
-new_version: ibm-granite/granite-3.1-2b-base
+We are continuously improving our models, this version is now out of date. Please check out the latest version of Granite at https://huggingface.co/ibm-granite.
 
 <!-- ## Citation
 ```