Adding Evaluation Results (#1)

- Adding Evaluation Results (c7d7723fd7818465d2cbcbc42ab426cc8d35dcaa)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,15 +1,118 @@
 ---
+license: llama3
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - ResplendentAI/Aura_Uncensored_l3_8B
 - meta-llama/Meta-Llama-3-8B-Instruct
 - ResplendentAI/Kei_Llama3_8B
 - Undi95/Llama-3-Unholy-8B
 - vicgalle/Roleplay-Llama-3-8B
-library_name: transformers
-tags:
-- mergekit
-- merge
-license: llama3
+model-index:
+- name: L3-RP_io
+  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: 63.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      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: 79.86
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      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: 67.92
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      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: 52.9
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      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: 75.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      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: 67.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -57,4 +160,17 @@ parameters:
   normalize: false
   int8_mask: true
 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_Azazelle__L3-RP_io)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.88|
+|AI2 Reasoning Challenge (25-Shot)|63.05|
+|HellaSwag (10-Shot)              |79.86|
+|MMLU (5-Shot)                    |67.92|
+|TruthfulQA (0-shot)              |52.90|
+|Winogrande (5-shot)              |75.69|
+|GSM8k (5-shot)                   |67.85|
+