Adding Evaluation Results (#1)

- Adding Evaluation Results (a8fd8198000c8d726faef8e9cfef8a40197ba7b5)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,12 +1,15 @@
 ---
-base_model:
-- uukuguy/speechless-code-mistral-7b-v1.0
-- upaya07/Arithmo2-Mistral-7B
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- uukuguy/speechless-code-mistral-7b-v1.0
+- upaya07/Arithmo2-Mistral-7B
+pipeline_tag: text-generation
 model-index:
 - name: sethuiyer/CodeCalc-Mistral-7B
   results:
@@ -25,8 +28,7 @@ model-index:
       value: 61.95
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -42,8 +44,7 @@ model-index:
       value: 83.64
       name: normalized accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -60,8 +61,7 @@ model-index:
       value: 62.78
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -77,8 +77,7 @@ model-index:
     - type: mc2
       value: 47.49
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -95,8 +94,7 @@ model-index:
       value: 78.3
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -113,12 +111,8 @@ model-index:
       value: 63.53
       name: accuracy
     source:
-      url: >-
-        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/CodeCalc-Mistral-7B
       name: Open LLM Leaderboard
-language:
-- en
-pipeline_tag: text-generation
 ---
 # CodeCalc-Mistral-7B
 
@@ -180,3 +174,17 @@ repetition_penalty: 1.17
 top_k: 49
 ```
 
+
+# [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_sethuiyer__CodeCalc-Mistral-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.33|
+|AI2 Reasoning Challenge (25-Shot)|61.95|
+|HellaSwag (10-Shot)              |83.64|
+|MMLU (5-Shot)                    |62.78|
+|TruthfulQA (0-shot)              |47.79|
+|Winogrande (5-shot)              |78.30|
+|GSM8k (5-shot)                   |63.53|
+