Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
-base_model:
-- ChaoticNeutrals/Bepis_9B
-- jeiku/Synthetic_Soul_1k_Mistral_128
+language:
+- en
+license: other
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: other
 datasets:
 - ChaoticNeutrals/Synthetic_Soul_1k
-language:
-- en
+base_model:
+- ChaoticNeutrals/Bepis_9B
+- jeiku/Synthetic_Soul_1k_Mistral_128
+model-index:
+- name: Soulful_Bepis_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: 63.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_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: 80.69
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_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: 62.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_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: 56.65
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_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: 76.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_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: 39.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Soulful_Bepis_7B
+      name: Open LLM Leaderboard
 ---
 # Soulful Bepis
 
@@ -30,4 +133,17 @@ models:
       weight: 1       
 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_jeiku__Soulful_Bepis_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.15|
+|AI2 Reasoning Challenge (25-Shot)|63.82|
+|HellaSwag (10-Shot)              |80.69|
+|MMLU (5-Shot)                    |62.53|
+|TruthfulQA (0-shot)              |56.65|
+|Winogrande (5-shot)              |76.16|
+|GSM8k (5-shot)                   |39.04|
+