Adding Evaluation Results

README.md

@@ -6,6 +6,109 @@ tags:
 - lazymergekit
 - gordicaleksa/YugoGPT
 - mlabonne/AlphaMonarch-7B
+model-index:
+- name: Tito-7B-slerp
+  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: 68.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      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: 86.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      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: 64.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      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: 57.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      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: 81.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      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: 63.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
+      name: Open LLM Leaderboard
 ---
 
 # Tito-7B-slerp
@@ -60,4 +163,17 @@ If we try to replicate these approaches on available Serbian datasets (running a
 |         | ARC   | Hellaswag | Winogrande | Avg.  |
 |---------|-------|-----------|------------|-------|
 | Tito-7B | 47.27 |     -     |   69.93    |   -   |
-| YugoGPT | 44.03 |     -     |   70.64    |   -   |
+| YugoGPT | 44.03 |     -     |   70.64    |   -   |
+# [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_Stopwolf__Tito-7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.13|
+|AI2 Reasoning Challenge (25-Shot)|68.09|
+|HellaSwag (10-Shot)              |86.38|
+|MMLU (5-Shot)                    |64.01|
+|TruthfulQA (0-shot)              |57.01|
+|Winogrande (5-shot)              |81.69|
+|GSM8k (5-shot)                   |63.61|
+