Adding Evaluation Results

README.md

@@ -1,11 +1,106 @@
 ---
-base_model:
-- NeverSleep/CausalLM-RP-34B
-- anthracite-org/magnum-v3-34b
+license: apache-2.0
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- NeverSleep/CausalLM-RP-34B
+- anthracite-org/magnum-v3-34b
+model-index:
+- name: Casual-Magnum-34B
+  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: 19.3
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Casual-Magnum-34B
+      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: 43.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Casual-Magnum-34B
+      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=Jacoby746/Casual-Magnum-34B
+      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: 16.33
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Casual-Magnum-34B
+      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: 8.4
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Casual-Magnum-34B
+      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: 46.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Casual-Magnum-34B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -39,4 +134,17 @@ parameters:
   embed_slerp: true  
 dtype: float16
 
-```
+```
+# [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_Jacoby746__Casual-Magnum-34B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.57|
+|IFEval (0-Shot)    |19.30|
+|BBH (3-Shot)       |43.05|
+|MATH Lvl 5 (4-Shot)| 7.85|
+|GPQA (0-shot)      |16.33|
+|MuSR (0-shot)      | 8.40|
+|MMLU-PRO (5-shot)  |46.49|
+