Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

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

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,4 +1,11 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - DreadPoor/MarshmaToon-3B-model_stock
 - jeiku/Everything_v3_128_StableLM
@@ -23,13 +30,101 @@ base_model:
 - jeiku/Alpaca_128_StableLM
 - DreadPoor/MarshmaToon-3B-model_stock
 - jeiku/No_Robots_Alpaca_StableLM
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: apache-2.0
-language:
-- en
+model-index:
+- name: Machroom-3B-model_stock
+  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: 32.98
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      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: 12.0
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      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: 2.42
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      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: 0.34
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      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: 17.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      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: 6.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DreadPoor/Machroom-3B-model_stock
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -75,4 +170,17 @@ models:
 merge_method: model_stock
 base_model: DreadPoor/MarshmaToon-3B-model_stock
 dtype: float16
-```
+```
+# [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_DreadPoor__Machroom-3B-model_stock)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |11.94|
+|IFEval (0-Shot)    |32.98|
+|BBH (3-Shot)       |12.00|
+|MATH Lvl 5 (4-Shot)| 2.42|
+|GPQA (0-shot)      | 0.34|
+|MuSR (0-shot)      |17.11|
+|MMLU-PRO (5-shot)  | 6.80|
+