Adding Evaluation Results (#1)

- Adding Evaluation Results (d356dfeb8914214d174b09292c28d723a0650859)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,6 +1,101 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
+model-index:
+- name: Qwen-2.5-7b-Spanish-o1-CoT
+  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: 42.1
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      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: 36.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      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: 24.62
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      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: 9.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      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: 18.44
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      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: 37.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Kukedlc/Qwen-2.5-7b-Spanish-o1-CoT
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -196,4 +291,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+# [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_Kukedlc__Qwen-2.5-7b-Spanish-o1-CoT)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.13|
+|IFEval (0-Shot)    |42.10|
+|BBH (3-Shot)       |36.86|
+|MATH Lvl 5 (4-Shot)|24.62|
+|GPQA (0-shot)      | 9.40|
+|MuSR (0-shot)      |18.44|
+|MMLU-PRO (5-shot)  |37.37|
+