Adding Evaluation Results (#2)

- Adding Evaluation Results (4f78d503d4ee0ee68a9524f07913dee156a33058)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,4 +1,9 @@
 ---
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - mistralai/Mistral-7B-v0.1
 - cognitivecomputations/dolphin-2.2.1-mistral-7b
@@ -10,12 +15,110 @@ base_model:
 - viethq188/LeoScorpius-7B-Chat-DPO
 - meta-math/MetaMath-Mistral-7B
 - Intel/neural-chat-7b-v3-3
-library_name: transformers
 inference: false
-tags:
-- mergekit
-- merge
-license: apache-2.0
+model-index:
+- name: Moza-7B-v1.0
+  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: 66.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      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: 83.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      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: 62.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      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: 65.16
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      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: 77.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      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: 62.55
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kidyu/Moza-7B-v1.0
+      name: Open LLM Leaderboard
 ---
 # Moza-7B-v1.0
 
@@ -110,4 +213,17 @@ parameters:
   normalize: true
   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_kidyu__Moza-7B-v1.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.66|
+|AI2 Reasoning Challenge (25-Shot)|66.55|
+|HellaSwag (10-Shot)              |83.45|
+|MMLU (5-Shot)                    |62.77|
+|TruthfulQA (0-shot)              |65.16|
+|Winogrande (5-shot)              |77.51|
+|GSM8k (5-shot)                   |62.55|
+