Adding Evaluation Results

README.md

@@ -11,11 +11,11 @@ tags:
 - mergekit
 - merge
 base_model:
-  - anthracite-org/magnum-v2.5-12b-
-  - Sao10K/MN-12B-Lyra-v4
-  - Gryphe/Pantheon-RP-1.6.1-12b-Nemo
-  - Epiculous/Crimson_Dawn-v0.2
-  - Elizezen/Himeyuri-v0.1-12B
+- anthracite-org/magnum-v2.5-12b-
+- Sao10K/MN-12B-Lyra-v4
+- Gryphe/Pantheon-RP-1.6.1-12b-Nemo
+- Epiculous/Crimson_Dawn-v0.2
+- Elizezen/Himeyuri-v0.1-12B
 datasets:
 - roleplay4fun/aesir-v1.1
 - kalomaze/Opus_Instruct_3k
@@ -35,6 +35,101 @@ datasets:
 - antiven0m_physical_reasoning_dpo
 - aixsatoshi_Swallow_MX_chatbot_DPO
 pipeline_tag: text-generation
+model-index:
+- name: ChatWaifu_v2.0_22B
+  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: 65.11
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      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: 42.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      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: 18.58
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      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: 9.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      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: 5.59
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      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: 31.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_v2.0_22B
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -220,3 +315,17 @@ By sharing this model, I hope to contribute to the research efforts of our commu
     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_v2.0_22B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |28.84|
+|IFEval (0-Shot)    |65.11|
+|BBH (3-Shot)       |42.29|
+|MATH Lvl 5 (4-Shot)|18.58|
+|GPQA (0-shot)      | 9.96|
+|MuSR (0-shot)      | 5.59|
+|MMLU-PRO (5-shot)  |31.51|
+