Adding Evaluation Results

README.md

@@ -3,6 +3,101 @@ license: gemma
 library_name: transformers
 datasets:
 - jondurbin/gutenberg-dpo-v0.1
+model-index:
+- name: gemma-2-Ifable-9B
+  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: 29.84
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      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: 41.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      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: 8.91
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      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: 12.19
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      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: 8.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      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: 35.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ifable/gemma-2-Ifable-9B
+      name: Open LLM Leaderboard
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
@@ -62,4 +157,17 @@ The following hyperparameters were used during training:
 - Tokenizers 0.19.1
 
 
-We are looking for product manager and operations managers to build applications through our model, and also open for business cooperation, and also AI engineer to join us, contact with : [email protected]
+We are looking for product manager and operations managers to build applications through our model, and also open for business cooperation, and also AI engineer to join us, contact with : [email protected]
+# [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_ifable__gemma-2-Ifable-9B)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |22.73|
+|IFEval (0-Shot)    |29.84|
+|BBH (3-Shot)       |41.03|
+|MATH Lvl 5 (4-Shot)| 8.91|
+|GPQA (0-shot)      |12.19|
+|MuSR (0-shot)      | 8.52|
+|MMLU-PRO (5-shot)  |35.85|
+