Adding Evaluation Results

README.md

@@ -1,6 +1,109 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
+model-index:
+- name: juud-Mistral-7B
+  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: 66.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      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: 85.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      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: 63.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      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: 54.12
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      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: 77.98
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      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: 23.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIJUUD/juud-Mistral-7B
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -15,3 +118,17 @@ If you have a question, feel free to
 contact to bnkaiteam@gmail.com
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6482ef3145fba6b2ad40b2bf/CQsM1C8y__gel9PM0X-Ue.png)
+
+# [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_AIJUUD__juud-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |61.72|
+|AI2 Reasoning Challenge (25-Shot)|66.72|
+|HellaSwag (10-Shot)              |85.00|
+|MMLU (5-Shot)                    |63.38|
+|TruthfulQA (0-shot)              |54.12|
+|Winogrande (5-shot)              |77.98|
+|GSM8k (5-shot)                   |23.12|
+