Adding Evaluation Results (#4)

- Adding Evaluation Results (ef1f4eda0e0b7e3fa2e76848ddfd96f1055f3f5b)


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

README.md

@@ -2,6 +2,109 @@
 license: other
 license_name: qwen-72b-licence
 license_link: https://huggingface.co/Qwen/Qwen-72B/blob/main/LICENSE
+model-index:
+- name: Tess-72B-v1.5b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 71.25
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 85.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 76.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 71.99
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 81.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 76.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=migtissera/Tess-72B-v1.5b
+      name: Open LLM Leaderboard
 ---
 
 <br>
@@ -19,4 +122,17 @@ Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Languag
 SYSTEM: <ANY SYSTEM CONTEXT>
 USER: 
 ASSISTANT:
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_migtissera__Tess-72B-v1.5b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |77.30|
+|AI2 Reasoning Challenge (25-Shot)|71.25|
+|HellaSwag (10-Shot)              |85.53|
+|MMLU (5-Shot)                    |76.63|
+|TruthfulQA (0-shot)              |71.99|
+|Winogrande (5-shot)              |81.45|
+|GSM8k (5-shot)                   |76.95|
+