Adding Evaluation Results (#1)

- Adding Evaluation Results (04d19da6a97db4d7c25b15894d4f5f91eb2a75cb)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -12,7 +12,6 @@ tags:
 - merge
 base_model:
 - mistralai/Mistral-Small-Instruct-2409
-pipeline_tag: text-generation
 datasets:
 - roleplay4fun/aesir-v1.1
 - kalomaze/Opus_Instruct_3k
@@ -20,6 +19,102 @@ datasets:
 - Aratako/Synthetic-Japanese-Roleplay-gpt-4o-mini-39.6k-formatted
 - Aratako/Synthetic-Japanese-Roleplay-NSFW-Claude-3.5s-15.3k-formatted
 - SkunkworksAI/reasoning-0.01
+pipeline_tag: text-generation
+model-index:
+- name: ChatWaifu_22B_v2.0_preview
+  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: 67.45
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      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: 45.49
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      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: 16.31
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      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: 8.72
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      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: 3.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      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: 33.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=spow12/ChatWaifu_22B_v2.0_preview
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -160,4 +255,17 @@ By sharing this model, I hope to contribute to the research efforts of our commu
     url          = { https://huggingface.co/spow12/ChatWaifu_22B_v2.0_preview },
     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_22B_v2.0_preview)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |29.12|
+|IFEval (0-Shot)    |67.45|
+|BBH (3-Shot)       |45.49|
+|MATH Lvl 5 (4-Shot)|16.31|
+|GPQA (0-shot)      | 8.72|
+|MuSR (0-shot)      | 3.53|
+|MMLU-PRO (5-shot)  |33.20|
+