Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
-license: cc-by-nc-sa-4.0
 language:
 - en
+license: cc-by-nc-sa-4.0
 tags:
 - merge
+model-index:
+- name: StopCarbon-10.7B-v5
+  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: 47.28
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      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: 31.99
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      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: 7.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      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: 9.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      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: 23.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=kekmodel/StopCarbon-10.7B-v5
+      name: Open LLM Leaderboard
 ---
 
 # StopCarbon
@@ -23,4 +118,17 @@ This model is an experimental version created using [mergekit](https://github.co
 
 ### Assistant:
 {asistant}
-```
+```
+# [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_kekmodel__StopCarbon-10.7B-v5)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.00|
+|IFEval (0-Shot)    |47.28|
+|BBH (3-Shot)       |31.99|
+|MATH Lvl 5 (4-Shot)| 0.00|
+|GPQA (0-shot)      | 7.49|
+|MuSR (0-shot)      | 9.28|
+|MMLU-PRO (5-shot)  |23.96|
+