Adding Evaluation Results

This is an automated PR created with [this space](https://huggingface.co/spaces/T145/open-llm-leaderboard-results-to-modelcard)!

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

Please report any issues here: https://huggingface.co/spaces/T145/open-llm-leaderboard-results-to-modelcard/discussions

README.md

@@ -1,35 +1,134 @@
 ---
 base_model: ghost-x/ghost-8b-beta
 language:
-  - vi
-  - ko
-  - es
-  - pt
-  - zh
-  - fr
-  - it
-  - de
-  - ja
-  - ru
-  - pl
-  - nl
-  - hi
-  - tr
-  - id
-  - en
+- vi
+- ko
+- es
+- pt
+- zh
+- fr
+- it
+- de
+- ja
+- ru
+- pl
+- nl
+- hi
+- tr
+- id
+- en
 license: other
 license_name: ghost-open-llms
 license_link: https://ghost-x.org/ghost-open-llms-license
 tags:
-  - ghost
-  - tools
-  - chat
-  - transformers
-  - unsloth
-  - llama
+- ghost
+- tools
+- chat
+- transformers
+- unsloth
+- llama
 pipeline_tag: text-generation
 widget:
-  - text: Why is the sky blue ?
+- text: Why is the sky blue ?
+model-index:
+- name: ghost-8b-beta-1608
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: wis-k/instruction-following-eval
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 42.73
+      name: averaged accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: SaylorTwift/bbh
+      split: test
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 23.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: lighteval/MATH-Hard
+      split: test
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 1.28
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 1.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      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: 1.58
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      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: 20.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=ghost-x%2Fghost-8b-beta-1608
+      name: Open LLM Leaderboard
 ---
 
 <p><img src="https://ghost-x.org/docs/models/ghost-8b-beta/images/logo.jpeg" width="40%" align="center" /></p>
@@ -830,3 +929,18 @@ If you find our work helpful, feel free to give us a cite.
   year = {2024}
 }
 ```
+
+# [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/ghost-x__ghost-8b-beta-1608-details)!
+Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=ghost-x%2Fghost-8b-beta-1608&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
+
+|      Metric       |Value (%)|
+|-------------------|--------:|
+|**Average**        |    15.10|
+|IFEval (0-Shot)    |    42.73|
+|BBH (3-Shot)       |    23.46|
+|MATH Lvl 5 (4-Shot)|     1.28|
+|GPQA (0-shot)      |     1.12|
+|MuSR (0-shot)      |     1.58|
+|MMLU-PRO (5-shot)  |    20.44|
+