Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
-base_model:
-- openchat/openchat-3.5-0106
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- openchat/openchat-3.5-0106
+model-index:
+- name: OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+  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: 59.76
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      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: 24.08
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      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: 6.8
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      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: 7.27
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      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: 11.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      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: 25.54
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Pretergeek/OpenChat-3.5-0106_8.99B_40Layers-Interleaved
+      name: Open LLM Leaderboard
 ---
 <p align="center">
   <a href="https://ko-fi.com/pretergeek">Buy me a Ko-Fi</a> •
@@ -156,4 +251,17 @@ dtype: bfloat16
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2401.02415}, 
 }
-```
+```
+# [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_Pretergeek__OpenChat-3.5-0106_8.99B_40Layers-Interleaved)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.49|
+|IFEval (0-Shot)    |59.76|
+|BBH (3-Shot)       |24.08|
+|MATH Lvl 5 (4-Shot)| 6.80|
+|GPQA (0-shot)      | 7.27|
+|MuSR (0-shot)      |11.51|
+|MMLU-PRO (5-shot)  |25.54|
+