Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 license: cc-by-nc-4.0
-tags:
+tags: 
 - merge
 - mergekit
 base_model:
@@ -9,55 +9,105 @@ model-index:
 - name: WestKunai-Hermes-10.7b-test
   results:
   - task:
-      type: dataset_type
-      name: dataset_split
+      type: text-generation
+      name: Text Generation
     dataset:
-      name: metric_type
-      type: dataset_name
-      config: dataset_revision
-      split: dataset_args
-      revision: metric_name
-      args: task_type
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
     metrics:
-    - type: metric_value
-      value: dataset_config
-      name: task_name
-      config: source_name
-      args: source_url
-    - type: metric_value
-      value: dataset_config
-      name: task_name
-      config: source_name
-      args: source_url
-    - type: metric_value
-      value: dataset_config
-      name: task_name
-      config: source_name
-      args: source_url
-    - type: metric_value
-      value: dataset_config
-      name: task_name
-      config: source_name
-      args: source_url
+    - type: acc_norm
+      value: 68.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      name: Open LLM Leaderboard
   - task:
-      type: dataset_type
-      name: dataset_split
+      type: text-generation
+      name: Text Generation
     dataset:
-      name: metric_type
-      type: dataset_name
-      config: dataset_args
-      split: metric_name
-      revision: task_type
-      args: task_name
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
     metrics:
-    - type: metric_value
-      value: dataset_config
-      name: source_name
-      config: source_url
-    - type: metric_value
-      value: dataset_config
-      name: source_name
-      config: source_url
+    - type: acc_norm
+      value: 87.10
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 64.28
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-10.7b-test
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 51.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=seyf1elislam/WestKunai-Hermes-7b
+      name: Open LLM Leaderboard
 ---
 
 # WestKunai-Hermes-10.7b-test
@@ -144,4 +194,3 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |TruthfulQA (0-shot)              |64.28|
 |Winogrande (5-shot)              |82.72|
 |GSM8k (5-shot)                   |51.86|
-