Adding Evaluation Results (#1)

- Adding Evaluation Results (0b08b1f9d5aeb1f8cd8b46720420ee64f6bfca70)


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

README.md

@@ -1,4 +1,5 @@
 ---
+license: cc-by-nc-4.0
 tags:
 - merge
 - mergekit
@@ -8,7 +9,109 @@ tags:
 base_model:
 - eren23/ogno-monarch-jaskier-merge-7b
 - mlabonne/AlphaMonarch-7B
-license: cc-by-nc-4.0
+model-index:
+- name: ogno-monarch-jaskier-merge-7b-v2
+  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: 72.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      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: 89.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      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: 64.77
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      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: 77.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      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: 84.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      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: 69.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-v2
+      name: Open LLM Leaderboard
 ---
 
 # ogno-monarch-jaskier-merge-7b-v2
@@ -64,4 +167,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_eren23__ogno-monarch-jaskier-merge-7b-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.35|
+|AI2 Reasoning Challenge (25-Shot)|72.87|
+|HellaSwag (10-Shot)              |89.15|
+|MMLU (5-Shot)                    |64.77|
+|TruthfulQA (0-shot)              |77.76|
+|Winogrande (5-shot)              |84.29|
+|GSM8k (5-shot)                   |69.29|
+