base model

README.md

@@ -12,8 +12,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: instruction-following
-        name: IFEval
+      type: instruction-following
+      name: IFEval
     metrics:
     - name: pass@1
       type: pass@1
@@ -22,8 +22,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: instruction-following
-        name: MT-Bench
+      type: instruction-following
+      name: MT-Bench
     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
@@ -42,8 +42,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU
+      type: human-exams
+      name: MMLU
     metrics:
     - name: pass@1
       type: pass@1
@@ -52,8 +52,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: human-exams
-        name: MMLU-Pro
+      type: human-exams
+      name: MMLU-Pro
     metrics:
     - name: pass@1
       type: pass@1
@@ -62,18 +62,18 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: OBQA 
+      type: commonsense
+      name: OBQA
     metrics:
     - name: pass@1
       type: pass@1
-      value: 46.60
+      value: 46.6
       veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: SIQA
+      type: commonsense
+      name: SIQA
     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
@@ -92,8 +92,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: WinoGrande
+      type: commonsense
+      name: WinoGrande
     metrics:
     - name: pass@1
       type: pass@1
@@ -102,8 +102,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: commonsense
-        name: TruthfulQA
+      type: commonsense
+      name: TruthfulQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -112,8 +112,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reading-comprehension
-        name: BoolQ
+      type: reading-comprehension
+      name: BoolQ
     metrics:
     - name: pass@1
       type: pass@1
@@ -122,8 +122,8 @@ 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
@@ -132,8 +132,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: ARC-C
+      type: reasoning
+      name: ARC-C
     metrics:
     - name: pass@1
       type: pass@1
@@ -142,8 +142,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: GPQA
+      type: reasoning
+      name: GPQA
     metrics:
     - name: pass@1
       type: pass@1
@@ -152,8 +152,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: reasoning
-        name: BBH
+      type: reasoning
+      name: BBH
     metrics:
     - name: pass@1
       type: pass@1
@@ -162,8 +162,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: HumanEvalSynthesis
+      type: code
+      name: HumanEvalSynthesis
     metrics:
     - name: pass@1
       type: pass@1
@@ -172,8 +172,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: HumanEvalExplain
+      type: code
+      name: HumanEvalExplain
     metrics:
     - name: pass@1
       type: pass@1
@@ -182,8 +182,8 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: HumanEvalFix
+      type: code
+      name: HumanEvalFix
     metrics:
     - name: pass@1
       type: pass@1
@@ -192,53 +192,55 @@ model-index:
   - task:
       type: text-generation
     dataset:
-        type: code
-        name: MBPP
+      type: code
+      name: MBPP
     metrics:
     - name: pass@1
       type: pass@1
-      value: 49.60
-      veriefied: false     
+      value: 49.6
+      veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: math
-        name: GSM8K
+      type: math
+      name: GSM8K
     metrics:
     - name: pass@1
       type: pass@1
       value: 68.99
-      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: 30.94
-      veriefied: false   
+      veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: multilingual
-        name: PAWS-X (7 langs)
+      type: multilingual
+      name: PAWS-X (7 langs)
     metrics:
     - name: pass@1
       type: pass@1
       value: 64.94
-      veriefied: false 
+      veriefied: false
   - task:
       type: text-generation
     dataset:
-        type: multilingual
-        name: MGSM (6 langs)
+      type: multilingual
+      name: MGSM (6 langs)
     metrics:
     - name: pass@1
       type: pass@1
-      value: 48.20
-      veriefied: false 
+      value: 48.2
+      veriefied: false
+base_model:
+- ibm-granite/granite-3.0-8b-base
 ---
 
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->