SteelStorage
/

Umbra-v3-MoE-4x11b

@@ -14,6 +14,109 @@ base_model:
 - Sao10K/Fimbulvetr-11B-v2
 - decapoda-research/Antares-11b-v2
 - beberik/Nyxene-v3-11B
 ---
 <!DOCTYPE html>
 <style>
@@ -128,4 +231,17 @@ a:hover {
     </div>
 </div>
 </body>
-</html>

 - Sao10K/Fimbulvetr-11B-v2
 - decapoda-research/Antares-11b-v2
 - beberik/Nyxene-v3-11B
+model-index:
+- name: Umbra-v3-MoE-4x11b
+  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: 68.43
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      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: 87.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      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: 65.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      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: 69.3
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      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: 83.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      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: 63.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Steelskull/Umbra-v3-MoE-4x11b
+      name: Open LLM Leaderboard
 ---
 <!DOCTYPE html>
 <style>
     </div>
 </div>
 </body>
+</html>
+# [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_Steelskull__Umbra-v3-MoE-4x11b)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.09|
+|AI2 Reasoning Challenge (25-Shot)|68.43|
+|HellaSwag (10-Shot)              |87.83|
+|MMLU (5-Shot)                    |65.99|
+|TruthfulQA (0-shot)              |69.30|
+|Winogrande (5-shot)              |83.90|
+|GSM8k (5-shot)                   |63.08|