Adding Evaluation Results

This is an automated PR created with https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co./spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,12 +1,115 @@
 ---
-base_model:
-- shahzebnaveed/NeuralHermes-2.5-Mistral-7B
-- berkeley-nest/Starling-LM-7B-alpha
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- shahzebnaveed/NeuralHermes-2.5-Mistral-7B
+- berkeley-nest/Starling-LM-7B-alpha
+model-index:
+- name: StarlingHermes-2.5-Mistral-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: 66.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-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: 85.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-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: 64.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-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: 49.56
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-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: 79.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-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: 65.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shahzebnaveed/StarlingHermes-2.5-Mistral-7B-slerp
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -47,4 +150,17 @@ parameters:
 dtype: bfloat16
 
 
-```
+```
+# [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_shahzebnaveed__StarlingHermes-2.5-Mistral-7B-slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.53|
+|AI2 Reasoning Challenge (25-Shot)|66.04|
+|HellaSwag (10-Shot)              |85.18|
+|MMLU (5-Shot)                    |64.72|
+|TruthfulQA (0-shot)              |49.56|
+|Winogrande (5-shot)              |79.72|
+|GSM8k (5-shot)                   |65.96|
+