Adding Evaluation Results (#1)

- Adding Evaluation Results (287db0f5911f449f71603233175e2bc87cea843a)

README.md

@@ -1,13 +1,108 @@
 ---
-base_model:
-- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
-- rombodawg/Rombos-LLM-V2.6-Qwen-14b
-- nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
+license: apache-2.0
 library_name: transformers
 tags:
 - mergekit
 - merge
-license: apache-2.0
+base_model:
+- huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
+- rombodawg/Rombos-LLM-V2.6-Qwen-14b
+- nbeerbower/Qwen2.5-Gutenberg-Doppel-14B
+model-index:
+- name: Robo-Gutenberg_V1.0
+  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: 60.08
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      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: 50.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      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: 21.3
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      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: 18.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      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: 19.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      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: 48.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Robo-Gutenberg_V1.0
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -60,4 +155,17 @@ parameters:
   normalize: false
   int8_mask: 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/Triangle104__Robo-Gutenberg_V1.0-details)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |36.30|
+|IFEval (0-Shot)    |60.08|
+|BBH (3-Shot)       |50.29|
+|MATH Lvl 5 (4-Shot)|21.30|
+|GPQA (0-shot)      |18.12|
+|MuSR (0-shot)      |19.20|
+|MMLU-PRO (5-shot)  |48.79|
+