Adding Evaluation Results

README.md

@@ -1,5 +1,9 @@
 ---
 license: apache-2.0
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - lodrick-the-lafted/Olethros-8B
 - lodrick-the-lafted/Limon-8B
@@ -7,10 +11,109 @@ base_model:
 - cgato/L3-TheSpice-8b-v0.8.3
 - unsloth/llama-3-8b-Instruct
 - Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total
-library_name: transformers
-tags:
-- mergekit
-- merge
+model-index:
+- name: Kudzu-8B
+  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: 62.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      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: 80.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      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: 68.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      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: 52.77
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      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: 76.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      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: 63.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Kudzu-8B
+      name: Open LLM Leaderboard
 ---
 
 <img src=https://huggingface.co/lodrick-the-lafted/Kudzu-8B/resolve/main/kudzu.png>
@@ -25,4 +128,17 @@ Fresh out of the mergekit-evolve kitchen, this is a merge model between:
 * [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3)
 
 
-Used wmdp as the scoring method for evolve.  In my limited testing, it has not done the usual Llama-3 "Ahaha!" interjections while retaining a good portion of the intelligence. There are several ablated models in the mix so don't be surprised if it gives you what you ask for.
+Used wmdp as the scoring method for evolve.  In my limited testing, it has not done the usual Llama-3 "Ahaha!" interjections while retaining a good portion of the intelligence. There are several ablated models in the mix so don't be surprised if it gives you what you ask for.
+# [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_lodrick-the-lafted__Kudzu-8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.25|
+|AI2 Reasoning Challenge (25-Shot)|62.46|
+|HellaSwag (10-Shot)              |80.28|
+|MMLU (5-Shot)                    |68.14|
+|TruthfulQA (0-shot)              |52.77|
+|Winogrande (5-shot)              |76.80|
+|GSM8k (5-shot)                   |63.08|
+