Adding Evaluation Results (#1)

- Adding Evaluation Results (851556518c302703c1b142bd4c482480b5089d36)


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

README.md

@@ -1,8 +1,4 @@
 ---
-license: llama3.1
-base_model:
-- meta-llama/Meta-Llama-3.1-8B-Instruct
-library_name: transformers
 language:
 - en
 - de
@@ -12,16 +8,115 @@ language:
 - hi
 - es
 - th
+license: llama3.1
+library_name: transformers
 tags:
 - reflection
 - unsloth
 - peft
 - llama
+base_model:
+- meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
 - leafspark/DetailedReflection-Claude-v3_5-Sonnet
 metrics:
 - accuracy
 pipeline_tag: text-generation
+model-index:
+- name: Llama-3.1-8B-MultiReflection-Instruct
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 71.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 28.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 12.54
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 8.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 30.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
 ---
 
 # Llama-3.1-8B-MultiReflection-Instruct
@@ -292,3 +387,17 @@ Now, it's your turn again. Can you think of any real-world applications of this
 Remember, this is a proof, not a mathematical exercise. Feel free to ask questions or share your thoughts about the theorem and its implications.
 </output>
 ```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_leafspark__Llama-3.1-8B-MultiReflection-Instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.12|
+|IFEval (0-Shot)    |71.25|
+|BBH (3-Shot)       |28.45|
+|MATH Lvl 5 (4-Shot)|12.54|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      | 8.52|
+|MMLU-PRO (5-shot)  |30.27|
+