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

@@ -1,11 +1,5 @@
 ---
-base_model:
-- icefog72/Kunokukulemonchini-32k-7b
-- icefog72/Mixtral_AI_Cyber_3.m1-BigL
-- grimjim/kukulemon-32K-7B
-- LeroyDyer/Mixtral_AI_Cyber_3.m1
-- Nitral-AI/Kunocchini-7b-128k-test
-- Undi95/BigL-7B
+license: cc-by-nc-4.0
 library_name: transformers
 tags:
 - mergekit
@@ -14,8 +8,116 @@ tags:
 - mistral
 - not-for-all-audiences
 - nsfw
-license: cc-by-nc-4.0
-
+base_model:
+- icefog72/Kunokukulemonchini-32k-7b
+- icefog72/Mixtral_AI_Cyber_3.m1-BigL
+- grimjim/kukulemon-32K-7B
+- LeroyDyer/Mixtral_AI_Cyber_3.m1
+- Nitral-AI/Kunocchini-7b-128k-test
+- Undi95/BigL-7B
+model-index:
+- name: IceLemonTeaRP-32k-7b
+  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: 67.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      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: 86.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      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: 64.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      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: 61.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      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: 79.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      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: 62.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
 ---
 # IceLemonTeaRP-32k-7b
 
@@ -77,3 +179,17 @@ parameters:
     - value: 0.5
 dtype: float16
 ```
+
+# [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_icefog72__IceLemonTeaRP-32k-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.43|
+|AI2 Reasoning Challenge (25-Shot)|67.66|
+|HellaSwag (10-Shot)              |86.53|
+|MMLU (5-Shot)                    |64.51|
+|TruthfulQA (0-shot)              |61.76|
+|Winogrande (5-shot)              |79.72|
+|GSM8k (5-shot)                   |62.40|
+