Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
 license: apache-2.0
-datasets:
-- Open-Orca/SlimOrca
 tags:
 - mistral
+datasets:
+- Open-Orca/SlimOrca
+model-index:
+- name: OpenHermes-2.5-neural-chat-7b-v3-2-7B
+  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: 66.38
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      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: 84.11
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      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: 62.84
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      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: 63.59
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      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: 78.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      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: 56.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-2-7B
+      name: Open LLM Leaderboard
 ---
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/x44nNbPTpv0zGTqA1Jb2q.png)
 
@@ -62,4 +165,17 @@ Quantizationed versions of this model is available thanks to [TheBloke](https://
 
 ##### AWQ
 
-- [TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-AWQ](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-AWQ)
+- [TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-AWQ](https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-AWQ)
+# [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_Weyaxi__OpenHermes-2.5-neural-chat-7b-v3-2-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |68.71|
+|AI2 Reasoning Challenge (25-Shot)|66.38|
+|HellaSwag (10-Shot)              |84.11|
+|MMLU (5-Shot)                    |62.84|
+|TruthfulQA (0-shot)              |63.59|
+|Winogrande (5-shot)              |78.53|
+|GSM8k (5-shot)                   |56.79|
+