Adding Evaluation Results (#1)

- Adding Evaluation Results (97ae3f05c75d08c02cf378cfa51bc1aa6156efa1)


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

README.md

@@ -1,13 +1,116 @@
 ---
-base_model:
-- mlabonne/AlphaMonarch-7B
-- bardsai/jaskier-7b-dpo-v5.6
-- CultriX/NeuralTrix-7B-dpo
+license: cc-by-nc-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: cc-by-nc-2.0
+base_model:
+- mlabonne/AlphaMonarch-7B
+- bardsai/jaskier-7b-dpo-v5.6
+- CultriX/NeuralTrix-7B-dpo
+model-index:
+- name: TriFusionNexus-7b
+  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: 72.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      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: 89.17
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      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: 64.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      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: 78.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      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: 84.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      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: 68.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BuckeyBarnes/TriFusionNexus-7b
+      name: Open LLM Leaderboard
 ---
 # TriFusionNexus-7b
 
@@ -48,4 +151,17 @@ parameters:
   normalize: true
   int8_mask: true
 dtype: float16
-```
+```
+# [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_BuckeyBarnes__TriFusionNexus-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.32|
+|AI2 Reasoning Challenge (25-Shot)|72.78|
+|HellaSwag (10-Shot)              |89.17|
+|MMLU (5-Shot)                    |64.44|
+|TruthfulQA (0-shot)              |78.13|
+|Winogrande (5-shot)              |84.93|
+|GSM8k (5-shot)                   |68.46|
+