Adding Evaluation Results

README.md

@@ -1,11 +1,114 @@
 ---
-base_model:
-- teknium/OpenHermes-2.5-Mistral-7B
-- Open-Orca/Mistral-7B-SlimOrca
+license: unlicense
 tags:
 - mergekit
 - merge
-license: unlicense
+base_model:
+- teknium/OpenHermes-2.5-Mistral-7B
+- Open-Orca/Mistral-7B-SlimOrca
+model-index:
+- name: mistral-merge-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: 63.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-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: 84.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-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: 64.04
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-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: 53.73
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-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: 77.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-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: 58.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=gqd/mistral-merge-7b
+      name: Open LLM Leaderboard
 ---
 # out2
 
@@ -38,4 +141,17 @@ models:
                 weight: 1.0
 #tokenizer_source: union
 
-```
+```
+# [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_gqd__mistral-merge-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.07|
+|AI2 Reasoning Challenge (25-Shot)|63.91|
+|HellaSwag (10-Shot)              |84.48|
+|MMLU (5-Shot)                    |64.04|
+|TruthfulQA (0-shot)              |53.73|
+|Winogrande (5-shot)              |77.35|
+|GSM8k (5-shot)                   |58.91|
+