Adding Evaluation Results

README.md

@@ -1,5 +1,7 @@
 ---
 license: apache-2.0
+tags:
+- merge
 model-index:
 - name: MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
   results:
@@ -21,8 +23,7 @@ model-index:
       value: 64.59
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -41,8 +42,7 @@ model-index:
       value: 85.39
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -62,8 +62,7 @@ model-index:
       value: 64.27
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -81,8 +80,7 @@ model-index:
     - type: mc2
       value: 55.14
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -102,8 +100,7 @@ model-index:
       value: 79.64
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -123,11 +120,8 @@ model-index:
       value: 71.65
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
       name: Open LLM Leaderboard
-tags:
-- merge
 ---
 
 # MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
@@ -155,4 +149,17 @@ parameters:
     - value: 0.5 # fallback for rest of tensors
 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_PulsarAI__MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.11|
+|AI2 Reasoning Challenge (25-Shot)|64.59|
+|HellaSwag (10-Shot)              |85.39|
+|MMLU (5-Shot)                    |64.27|
+|TruthfulQA (0-shot)              |55.14|
+|Winogrande (5-shot)              |79.64|
+|GSM8k (5-shot)                   |71.65|
+