Adding Evaluation Results (#2)

- Adding Evaluation Results (5e59a3cecc061a55550d977bac4592f9632e3f47)


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

README.md

@@ -1,9 +1,104 @@
 ---
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
-library_name: transformers
 language:
 - en
 - it
+library_name: transformers
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+model-index:
+- name: Llama-3.1-8b-ITA
+  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: 79.17
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      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: 30.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      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: 10.88
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      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: 5.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      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: 11.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      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: 31.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
+      name: Open LLM Leaderboard
 ---
 
 ## Model Architecture
@@ -40,4 +135,17 @@ print(answer)
 ```
 ---
 ## Developer
-[Michele Montebovi]
+[Michele Montebovi]
+# [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_DeepMount00__Llama-3.1-8b-ITA)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.23|
+|IFEval (0-Shot)    |79.17|
+|BBH (3-Shot)       |30.93|
+|MATH Lvl 5 (4-Shot)|10.88|
+|GPQA (0-shot)      | 5.03|
+|MuSR (0-shot)      |11.40|
+|MMLU-PRO (5-shot)  |31.96|
+