Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
-license: apache-2.0
-datasets:
-- GEM/e2e_nlg
 language:
 - en
+license: apache-2.0
 base_model:
 - mistralai/Mistral-7B-v0.1
+datasets:
+- GEM/e2e_nlg
+model-index:
+- name: mistral_7b_v0.1_structedData_e2e
+  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: 17.27
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      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: 18.06
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      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: 0.23
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      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: 3.91
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      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: 5.64
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      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: 20.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FuJhen/mistral_7b_v0.1_structedData_e2e
+      name: Open LLM Leaderboard
 ---
 # Model Card for Model ID
 
@@ -200,4 +295,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+# [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_FuJhen__mistral_7b_v0.1_structedData_e2e)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |10.87|
+|IFEval (0-Shot)    |17.27|
+|BBH (3-Shot)       |18.06|
+|MATH Lvl 5 (4-Shot)| 0.23|
+|GPQA (0-shot)      | 3.91|
+|MuSR (0-shot)      | 5.64|
+|MMLU-PRO (5-shot)  |20.12|
+