Adding Evaluation Results

README.md

@@ -1,14 +1,108 @@
 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - Locutusque/StockQwen-2.5-7B
 - djuna/Q2.5-Fuppavy-7B
 - fblgit/cybertron-v4-qw7B-MGS
 - happzy2633/qwen2.5-7b-ins-v3
-library_name: transformers
-tags:
-- mergekit
-- merge
-
+model-index:
+- name: Q2.5-Partron-7B
+  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: 73.21
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      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: 35.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      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: 0.08
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      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: 6.38
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      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: 11.07
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      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: 36.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Partron-7B
+      name: Open LLM Leaderboard
 ---
 # merge
 
@@ -52,3 +146,17 @@ parameters:
 dtype: float32
 out_dtype: bfloat16
 ```
+
+# [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_djuna__Q2.5-Partron-7B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |27.08|
+|IFEval (0-Shot)    |73.21|
+|BBH (3-Shot)       |35.26|
+|MATH Lvl 5 (4-Shot)| 0.08|
+|GPQA (0-shot)      | 6.38|
+|MuSR (0-shot)      |11.07|
+|MMLU-PRO (5-shot)  |36.47|
+