Adding Evaluation Results (#1)

- Adding Evaluation Results (696e6c3f86279ff4e248e04df4412ace5375da70)

README.md

@@ -1,4 +1,8 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - gz987/qwen2.5-7b-cabs-v0.3
 - ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
@@ -10,11 +14,101 @@ base_model:
 - bunnycore/Qwen-2.5-7b-rp-lora
 - Qwen/Qwen2.5-7B-Instruct
 - ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Blabbertron-1.0
+  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: 74.33
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      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: 36.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      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: 49.24
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      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: 6.94
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      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: 13.51
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      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: 37.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Blabbertron-1.0
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -54,3 +148,17 @@ dtype: bfloat16
 tokenizer_source: Qwen/Qwen2.5-7B-Instruct
 
 ```
+
+# [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/bunnycore__Blabbertron-1.0-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.22|
+|IFEval (0-Shot)    |74.33|
+|BBH (3-Shot)       |36.05|
+|MATH Lvl 5 (4-Shot)|49.24|
+|GPQA (0-shot)      | 6.94|
+|MuSR (0-shot)      |13.51|
+|MMLU-PRO (5-shot)  |37.27|
+