Adding Evaluation Results (#1)

- Adding Evaluation Results (4481f74055bb2a538fdceea283b692e14caa34e8)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,9 +1,112 @@
 ---
-pipeline_tag: text-generation
+license: cc-by-4.0
 tags:
 - mistral
 - merge
-license: cc-by-4.0
+pipeline_tag: text-generation
+model-index:
+- name: Sina-Odin-7b-Merge
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 52.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 68.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      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: 45.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      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: 39.2
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      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: 72.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      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: 8.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/Sina-Odin-7b-Merge
+      name: Open LLM Leaderboard
 ---
 # Model Card for Sina-Odin-7b-Merge
 <!-- Provide a quick summary of what the model is/does. -->
@@ -31,4 +134,17 @@ base_model: Mihaiii/Metis-0.3
 parameters:
   int8_mask: true
 dtype: bfloat16
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Azazelle__Sina-Odin-7b-Merge)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.82|
+|AI2 Reasoning Challenge (25-Shot)|52.82|
+|HellaSwag (10-Shot)              |68.86|
+|MMLU (5-Shot)                    |45.54|
+|TruthfulQA (0-shot)              |39.20|
+|Winogrande (5-shot)              |72.22|
+|GSM8k (5-shot)                   | 8.26|
+