Adding Evaluation Results

README.md

@@ -1,14 +1,109 @@
 ---
-base_model:
-- maldv/badger-lambda-llama-3-8b
-- maldv/llama-3-fantasy-writer-8b
-- dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - fourier
 - task addition
 - merge
-license: cc-by-nc-4.0
+base_model:
+- maldv/badger-lambda-llama-3-8b
+- maldv/llama-3-fantasy-writer-8b
+- dreamgen-preview/opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5
+model-index:
+- name: badger-writer-llama-3-8b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 53.03
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 26.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 6.57
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 30.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=maldv/badger-writer-llama-3-8b
+      name: Open LLM Leaderboard
 ---
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/SpNOAI3VKUsWegChuQHTk.png)
@@ -61,3 +156,17 @@ Purpose: Exposition ; Descriptive ; Visual Detail, character appearance
 ````
 
 [Terminal Connection](https://www.maldevide.com/books/terminal_connection.txt)
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_maldv__badger-writer-llama-3-8b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |20.93|
+|IFEval (0-Shot)    |53.03|
+|BBH (3-Shot)       |26.88|
+|MATH Lvl 5 (4-Shot)| 6.57|
+|GPQA (0-shot)      | 5.26|
+|MuSR (0-shot)      | 3.20|
+|MMLU-PRO (5-shot)  |30.67|
+