Adding Evaluation Results

README.md

@@ -1,5 +1,100 @@
 ---
 license: apache-2.0
+model-index:
+- name: Tess-3-Mistral-Nemo-12B
+  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: 33.55
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      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: 28.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      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: 4.68
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      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: 0.11
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      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: 15.49
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      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: 17.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=migtissera/Tess-3-Mistral-Nemo-12B
+      name: Open LLM Leaderboard
 ---
 
 ![Tesoro](https://huggingface.co/migtissera/Tess-M-v1.0/resolve/main/Tess.png) 
@@ -71,4 +166,17 @@ while True:
     answer = generate_text(llm_prompt)
     print(answer)
     conversation = f"{llm_prompt}{answer}<|im_end|>\n<|im_start|>user\n"
-```
+```
+# [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_migtissera__Tess-3-Mistral-Nemo-12B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |16.54|
+|IFEval (0-Shot)    |33.55|
+|BBH (3-Shot)       |28.04|
+|MATH Lvl 5 (4-Shot)| 4.68|
+|GPQA (0-shot)      | 0.11|
+|MuSR (0-shot)      |15.49|
+|MMLU-PRO (5-shot)  |17.39|
+