Adding Evaluation Results

README.md

@@ -1,9 +1,104 @@
 ---
+license: mit
 base_model:
 - Qwen/Qwen2.5-32B
 - AiCloser/Qwen2.5-32B-AGI
 - Qwen/Qwen2.5-32B-Instruct
-license: mit
+model-index:
+- name: franqwenstein-35b
+  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: 37.99
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      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: 52.23
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      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: 30.29
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      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: 20.47
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      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: 22.12
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      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: 52.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nisten/franqwenstein-35b
+      name: Open LLM Leaderboard
 ---
 
 
@@ -36,4 +131,17 @@ Oh yeah and it scores ~1% better than Qwen2.5-72b-instruct on gpqa_diamond_zeros
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/kBAwRVET5CFCLstgms9Xy.png)
 
-GG. Enjoy.
+GG. Enjoy.
+# [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_nisten__franqwenstein-35b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |35.94|
+|IFEval (0-Shot)    |37.99|
+|BBH (3-Shot)       |52.23|
+|MATH Lvl 5 (4-Shot)|30.29|
+|GPQA (0-shot)      |20.47|
+|MuSR (0-shot)      |22.12|
+|MMLU-PRO (5-shot)  |52.56|
+