Adding Evaluation Results

This is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr

The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.

If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- mlabonne/NeuralDaredevil-8B-abliterated
-- grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
 tags:
 - merge
 - mergekit
 - lazymergekit
 - mlabonne/NeuralDaredevil-8B-abliterated
 - grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
+base_model:
+- mlabonne/NeuralDaredevil-8B-abliterated
+- grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
+model-index:
+- name: NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+  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: 79.99
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      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: 30.76
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      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: 10.27
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      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: 4.14
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      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: 9.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      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: 30.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BoltMonkey/NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
+      name: Open LLM Leaderboard
 ---
 
 # NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated
@@ -59,4 +154,17 @@ pipeline = transformers.pipeline(
 
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
-```
+```
+# [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_BoltMonkey__NeuralDaredevil-SuperNova-Lite-7B-DARETIES-abliterated)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.50|
+|IFEval (0-Shot)    |79.99|
+|BBH (3-Shot)       |30.76|
+|MATH Lvl 5 (4-Shot)|10.27|
+|GPQA (0-shot)      | 4.14|
+|MuSR (0-shot)      | 9.47|
+|MMLU-PRO (5-shot)  |30.37|
+