Adding Evaluation Results (#5)

- Adding Evaluation Results (d2313c3d2ab2196cb85b42cf49648e45a24f2d40)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,9 +1,104 @@
 ---
-license: apache-2.0
 language:
 - en
 - es
+license: apache-2.0
 pipeline_tag: text-generation
+model-index:
+- name: occiglot-7b-es-en-instruct
+  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: 34.85
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      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: 17.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      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: 1.89
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      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: 1.23
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      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: 4.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      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: 14.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=occiglot/occiglot-7b-es-en-instruct
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://huggingface.co/datasets/malteos/images/resolve/main/occiglot.medium.png)
@@ -146,3 +241,17 @@ through the project [OpenGPT-X](https://opengpt-x.de/en/) (project no. 68GX21007
 
 - https://huggingface.co/collections/occiglot/occiglot-eu5-7b-v01-65dbed502a6348b052695e01
 - https://huggingface.co/NikolayKozloff/occiglot-7b-es-en-GGUF
+
+# [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_occiglot__occiglot-7b-es-en-instruct)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |12.37|
+|IFEval (0-Shot)    |34.85|
+|BBH (3-Shot)       |17.24|
+|MATH Lvl 5 (4-Shot)| 1.89|
+|GPQA (0-shot)      | 1.23|
+|MuSR (0-shot)      | 4.45|
+|MMLU-PRO (5-shot)  |14.56|
+