Adding Evaluation Results

README.md

@@ -1,4 +1,9 @@
 ---
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - mlabonne/ChimeraLlama-3-8B-v2
 - grimjim/llama-3-merge-pp-instruct-8B
@@ -13,12 +18,110 @@ base_model:
 - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
 - flammenai/Mahou-1.0-llama3-8B
 - flammenai/Mahou-1.1-llama3-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: other
 license_name: llama3
+model-index:
+- name: llama-3-stinky-v2-8B
+  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: 66.98
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      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: 83.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      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: 68.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      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: 55.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      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: 77.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      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: 69.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nbeerbower/llama-3-stinky-v2-8B
+      name: Open LLM Leaderboard
 ---
 # llama-3-stinky-v2-8B
 
@@ -69,3 +172,17 @@ dtype: bfloat16
 
 
 ```
+
+# [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_nbeerbower__llama-3-stinky-v2-8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.27|
+|AI2 Reasoning Challenge (25-Shot)|66.98|
+|HellaSwag (10-Shot)              |83.20|
+|MMLU (5-Shot)                    |68.33|
+|TruthfulQA (0-shot)              |55.83|
+|Winogrande (5-shot)              |77.51|
+|GSM8k (5-shot)                   |69.75|
+