Update README.md

README.md

@@ -15,7 +15,109 @@ tags:
 - mistral
 - text-generation
 - roleplay
-
+model-index:
+- name: Smart-Lemon-Cookie-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: 69.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      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: 86.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      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: 65.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      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: 61.59
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      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: 79.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      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: 58.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=FallenMerick/Chunky-Lemon-Cookie-11B
+      name: Open LLM Leaderboard
 ---
 
 ![cute](https://huggingface.co/FallenMerick/Chunky-Lemon-Cookie-11B/resolve/main/Chunky-Lemon-Cookie.png)
@@ -90,3 +192,16 @@ base_model: Mistral-11B
 dtype: float16
 name: Chunky-Lemon-Cookie-11B
 ```
+
+# [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_FallenMerick__Chunky-Lemon-Cookie-11B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.23|
+|AI2 Reasoning Challenge (25-Shot)|69.62|
+|HellaSwag (10-Shot)              |86.55|
+|MMLU (5-Shot)                    |65.35|
+|TruthfulQA (0-shot)              |61.59|
+|Winogrande (5-shot)              |79.79|
+|GSM8k (5-shot)                   |58.45|