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

@@ -1,10 +1,4 @@
 ---
-base_model:
-- mistralai/Mistral-Nemo-Instruct-2407
-- NeverSleep/Lumimaid-v0.2-12B
-- Epiculous/Violet_Twilight-v0.1
-- Sao10K/MN-12B-Lyra-v4
-- anthracite-org/magnum-v2-12b
 language:
 - en
 - fr
@@ -16,14 +10,115 @@ language:
 - zh
 - ja
 license: cc-by-nc-4.0
-pipeline_tag: text-generation
+library_name: transformers
 tags:
 - nsfw
 - Visual novel
 - roleplay
 - mergekit
 - merge
-library_name: transformers
+base_model:
+- mistralai/Mistral-Nemo-Instruct-2407
+- NeverSleep/Lumimaid-v0.2-12B
+- Epiculous/Violet_Twilight-v0.1
+- Sao10K/MN-12B-Lyra-v4
+- anthracite-org/magnum-v2-12b
+pipeline_tag: text-generation
+model-index:
+- name: ChatWaifu_v1.4
+  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: 56.91
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      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: 31.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      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: 7.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      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: 7.61
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      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: 20.03
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      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: 27.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v1.4
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -158,4 +253,17 @@ This repository can use Visual novel-based RAG, but i will not distribute it yet
     url          = { https://huggingface.co/spow12/ChatWaifu_v1.4 },
     publisher    = { Hugging Face }
 }
-```
+```
+# [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_spow12__ChatWaifu_v1.4)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |25.25|
+|IFEval (0-Shot)    |56.91|
+|BBH (3-Shot)       |31.63|
+|MATH Lvl 5 (4-Shot)| 7.85|
+|GPQA (0-shot)      | 7.61|
+|MuSR (0-shot)      |20.03|
+|MMLU-PRO (5-shot)  |27.50|
+