Adding Evaluation Results

README.md

@@ -1,9 +1,7 @@
 ---
-license: llama2
 language:
 - en
-pipeline_tag: text-generation
-inference: false
+license: llama2
 tags:
 - dare
 - super mario merge
@@ -11,6 +9,111 @@ tags:
 - llama
 - llama-2
 - merge
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: llama2-megamerge-dare-13b-v2
+  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: 59.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      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: 80.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      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: 55.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      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: 47.27
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      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: 75.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      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: 29.26
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=martyn/llama2-megamerge-dare-13b-v2
+      name: Open LLM Leaderboard
 ---
 
 # llama 13b mega merge v2
@@ -48,4 +151,17 @@ python hf_merge.py mergelist.txt 13b-merge-v2 -p 0.11 -lambda 2.1
 ## Notes
 
 * seems to generalize instruct styles
-* `p` and `lambda` are still a guess
+* `p` and `lambda` are still a guess
+# [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_martyn__llama2-megamerge-dare-13b-v2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |57.94|
+|AI2 Reasoning Challenge (25-Shot)|59.39|
+|HellaSwag (10-Shot)              |80.93|
+|MMLU (5-Shot)                    |55.26|
+|TruthfulQA (0-shot)              |47.27|
+|Winogrande (5-shot)              |75.53|
+|GSM8k (5-shot)                   |29.26|
+