Adding Evaluation Results

README.md

@@ -1,5 +1,100 @@
 ---
 license: gpl-3.0
+model-index:
+- name: 34b-beta
+  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: 30.43
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      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: 36.68
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      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: 4.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      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: 12.86
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      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: 6.92
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      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: 48.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=CausalLM/34b-beta
+      name: Open LLM Leaderboard
 ---
 # CausalLM 34B β
 
@@ -33,4 +128,17 @@ Please do not use wikitext for quantization calibration because all wikitext hav
 
 data from https://huggingface.co/spaces/Yeyito/llm_contamination_detector
 
-It should be *safe*. It was not trained on the benchmark, but the contamination of the training dataset is unavoidable due to cost constraints.
+It should be *safe*. It was not trained on the benchmark, but the contamination of the training dataset is unavoidable due to cost constraints.
+# [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_CausalLM__34b-beta)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |23.18|
+|IFEval (0-Shot)    |30.43|
+|BBH (3-Shot)       |36.68|
+|MATH Lvl 5 (4-Shot)| 4.15|
+|GPQA (0-shot)      |12.86|
+|MuSR (0-shot)      | 6.92|
+|MMLU-PRO (5-shot)  |48.06|
+