Adding Evaluation Results

README.md

@@ -1,16 +1,132 @@
 ---
+language:
+- en
+license: apache-2.0
+library_name: transformers
 base_model:
 - ChaoticNeutrals/InfinityNexus_9B
 - jeiku/luna_lora_9B
-library_name: transformers
-license: apache-2.0
 datasets:
 - ResplendentAI/Luna_Alpaca
-language:
-- en
+model-index:
+- name: Garbage_9B
+  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: 63.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      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: 82.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      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: 64.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      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: 47.87
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      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: 80.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      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: 54.13
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Garbage_9B
+      name: Open LLM Leaderboard
 ---
 # Garbage
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/EX9x2T18il0IKsqP6hKUy.png)
 
-This is a finetune of InfinityNexus_9B. This is my first time tuning a frankenmerge, so hopefully it works out. The goal is to improve intelligence and RP ability beyond the 7B original models.
+This is a finetune of InfinityNexus_9B. This is my first time tuning a frankenmerge, so hopefully it works out. The goal is to improve intelligence and RP ability beyond the 7B original models.
+# [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__Garbage_9B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |65.54|
+|AI2 Reasoning Challenge (25-Shot)|63.65|
+|HellaSwag (10-Shot)              |82.97|
+|MMLU (5-Shot)                    |64.18|
+|TruthfulQA (0-shot)              |47.87|
+|Winogrande (5-shot)              |80.43|
+|GSM8k (5-shot)                   |54.13|
+