Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-base_model:
-- mlabonne/Marcoro14-7B-slerp
-- Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
+license: apache-2.0
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- mlabonne/Marcoro14-7B-slerp
+- Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
+model-index:
+- name: Sour-Marcoro-12.5B
+  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: 67.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      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: 83.7
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      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: 65.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      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: 68.17
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      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: 82.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      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: 47.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jpechg/Sour-Marcoro-12.5B
+      name: Open LLM Leaderboard
 ---
 # models
 
@@ -37,4 +140,17 @@ slices:
 merge_method: passthrough
 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_jpechg__Sour-Marcoro-12.5B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |69.23|
+|AI2 Reasoning Challenge (25-Shot)|67.92|
+|HellaSwag (10-Shot)              |83.70|
+|MMLU (5-Shot)                    |65.85|
+|TruthfulQA (0-shot)              |68.17|
+|Winogrande (5-shot)              |82.08|
+|GSM8k (5-shot)                   |47.69|
+